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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 796
    Prev
    Next
    INDEX
    Explanations

    package

    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
    principalColumn
    -0.80
    oredCriteria
    -0.77
    UnusedPrivate
    -0.75
    ValueStyle
    -0.67
    CppMethod
    -0.66
    StoreMessageInfo
    -0.66
    ագրություններ
    -0.66
    writeFieldEnd
    -0.66
    FunctionFlags
    -0.65
     ویکی‌پدیا
    -0.64
    POSITIVE LOGITS
    es
    0.96
    ات
    0.68
    e
    0.68
    isation
    0.60
    ES
    0.60
    ization
    0.57
    esi
    0.57
    esis
    0.56
     Examin
    0.54
    ize
    0.53
    Activations Density 0.057%

    No Known Activations