© 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. 0-CLT-HP
    7. 40444
    Prev
    Next
    INDEX
    Explanations

    code documentation

    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
    tiny
    -0.47
    例文帳に追加
    -0.47
    Népesség
    -0.46
    tagHelperRunner
    -0.45
     diamètre
    -0.44
    ».
    -0.42
    一旦
    -0.42
     liquid
    -0.41
    وال
    -0.41
    edor
    -0.41
    POSITIVE LOGITS
    ChildScrollView
    0.86
    IsMutable
    0.78
    SerializedSize
    0.76
     utafitiHapana
    0.73
     surla
    0.73
     Efq
    0.67
    endpush
    0.66
    zzleHttp
    0.66
    出版年
    0.65
     autorytatywna
    0.65
    Activations Density 0.066%

    No Known Activations