© 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. 91282
    Prev
    Next
    INDEX
    Explanations

    technology and media

    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
    EXPECT
    -0.44
    Попис
    -0.43
    ANTLR
    -0.42
     if
    -0.42
    '
    -0.40
    ioutil
    -0.40
    utro
    -0.40
     KRE
    -0.39
    "
    -0.38
    .
    -0.38
    POSITIVE LOGITS
    Diwedd
    0.80
    RenderAtEndOf
    0.77
    ьаж
    0.75
    httphttps
    0.75
     nahilalakip
    0.68
    migrationBuilder
    0.67
    IsMutable
    0.66
     >=",
    0.65
    npmjs
    0.63
    ècie
    0.63
    Activations Density 0.001%

    No Known Activations