Sleep Journal Signal Checker

How Sleep Journal Signal Checker works

Press Load model once: your browser downloads Gemma 4 E2B instruction-tuned (web build) (2.0 GB) from this site and keeps it in its cache. Then add your text and press Check locally. The model runs on this device using your graphics card, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.

Gemma 4 E2B instruction-tuned (web build) is a small open language model from Google. The tool sends it the instruction below plus your text, asks for a JSON answer with fixed fields, and shows each field as a card. It runs at temperature 0, so the same input gives the same answer on the same device, though different graphics cards can word it slightly differently.

Inputs longer than 6,000 characters are cut to that length before they reach the model, and the result says so. The model only sees what you paste: it does not look anything up.

If what you enter mentions suicide or self-harm, the tool does not run the model. It shows crisis lines instead (in the US, call or text 988), because a trained person can help in a way a small model cannot.

The instruction the model gets

You read a sleep journal and organise what it records: bed and wake times as written, night wakings, habits mentioned (caffeine, screens, alcohol, exercise) and how the person felt the next day, so they can spot their own patterns. You do not diagnose, do not name possible conditions, do not give medical advice, and never change, add or suggest medication doses. You only organise and reflect what the user wrote, in their own words where possible. Do not calculate anything; copy numbers exactly as written. Do not add up hours of sleep and do not say whether their sleep is normal.

What it returns

• Times logged: Bedtime, wake time and night wakings, copied as written, for example 'bed 12:45am'.
• Habits mentioned: Caffeine, screens, alcohol, meals, exercise or other habits the journal mentions, with their time if given.
• How they felt: What the journal says about mood or energy the next day, quoted.
• Patterns to watch: Habits and times that appear together in the journal, for example late caffeine and waking at 3am. Describe, do not explain causes.

Worked example

The model's output for the built-in sample, recorded on a desktop browser. Your run may word things slightly differently.

Sleep journal: Bed 12:45am, woke 3:20 and 5:10, phone in bed for 45 minutes, caffeine at 4pm, felt groggy during morning meeting.

Times logged

bed 12:45am woke 3:20 woke 5:10

Habits mentioned

phone in bed for 45 minutes caffeine at 4pm

How they felt

felt groggy during morning meeting

Patterns to watch

caffeine at 4pm

The model

The files are served from this site, versioned so a cached copy is never stale. Nothing is fetched from a third party while you use the tool.

Limitations

• Small language models make mistakes: they can miss an item, merge two, or state something more confidently than the text supports. Check the result against your input before you rely on it.
• It needs WebGPU and about 8 GB of memory, so it is offered on desktops and laptops, not on phones and tablets. Devices that cannot run it get the keyword fallback, clearly labelled.
• Results describe the input you gave, not the real-world situation behind it. Review them yourself before acting.
• This is not a medical device and does not give medical advice, a diagnosis or a treatment plan. Ask a qualified health professional about any symptom, medication or change to your routine.

Good uses

• Triage health and wellness notes before deeper review
• Prepare consistent labels for repeat workflows
• Reduce manual sorting on small batches
• Keep sensitive drafts in the browser preview