© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91444
    Prev
    Next
    INDEX
    Explanations

    time/night

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.62
    noon
    -0.56
     noon
    -0.55
     breakfasts
    -0.55
     jScrollPane
    -0.54
    Noon
    -0.53
     eche
    -0.53
     Noon
    -0.50
     drawings
    -0.50
    ateral
    -0.50
    POSITIVE LOGITS
    parsedMessage
    0.70
    UnsafeEnabled
    0.54
    хьтан
    0.54
    contentLoaded
    0.54
    انجليز
    0.48
    Vezi
    0.46
    prägt
    0.45
    fjspx
    0.44
    Todd
    0.44
    ografija
    0.43
    Activations Density 0.010%

    No Known Activations