© 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. 1-CLT-HP
    7. 14500
    Prev
    Next
    INDEX
    Explanations

    animal or sports

    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
     lateinit
    -0.48
     Ent
    -0.46
    thren
    -0.46
    äsent
    -0.45
    ArgsConstructor
    -0.44
    робнее
    -0.44
     userDetails
    -0.44
     mezz
    -0.43
     DATA
    -0.43
    Accidental
    -0.43
    POSITIVE LOGITS
    WebElementEntity
    0.69
    出版年
    0.63
     himo
    0.60
    Дереккөздер
    0.55
     חיצוניים
    0.55
    AMIENTO
    0.54
    DotNetBar
    0.54
    ishw
    0.52
    WireFormatLite
    0.52
    ніципалі
    0.50
    Activations Density 0.004%

    No Known Activations