© 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. 20-CLT-HP
    7. 77836
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific writing

    np_max-act-logits · 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
    ConstraintMaker
    -0.56
    GraphicsUnit
    -0.52
    йо
    -0.45
    icher
    -0.44
     ***!
    -0.43
    InlineData
    -0.43
    leski
    -0.43
    硃
    -0.42
    colhead
    -0.41
     ligiloj
    -0.41
    POSITIVE LOGITS
    aarrggbb
    0.69
    WireFormat
    0.63
    jspx
    0.57
     BitmapFactory
    0.57
     صوتيه
    0.56
     Worship
    0.56
    tonsoft
    0.56
    parsedMessage
    0.55
     Peas
    0.54
     beſt
    0.54
    Activations Density 0.000%

    No Known Activations