© 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. 91363
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     autorytatywna
    -0.69
     category
    -0.66
    WindowConstants
    -0.65
    AutoScaleMode
    -0.64
    AndEndTag
    -0.63
     ModelExpression
    -0.61
     categorie
    -0.61
     contextLoads
    -0.61
    Personensuche
    -0.59
    afficheront
    -0.59
    POSITIVE LOGITS
    //
    0.50
     (;;
    0.46
    inheritdoc
    0.43
    migrationBuilder
    0.43
    #
    0.42
    RTSC
    0.42
    Dimensions
    0.40
    {}{
    0.40
    edonia
    0.40
     Dimensions
    0.39
    Activations Density 0.017%

    No Known Activations