© 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. 4933
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    <bos>
    -1.00
     Италијани
    -0.85
     Italijanski
    -0.85
     '\\;'
    -0.82
     nemlig
    -0.79
    帖最后由
    -0.77
    RepeatedField
    -0.77
    новниш
    -0.74
    InjectAttribute
    -0.73
    aarrggbb
    -0.73
    POSITIVE LOGITS
    InitStruct
    0.46
     dignité
    0.44
    <eos>
    0.42
     caisse
    0.41
    ապ
    0.40
     further
    0.40
     cau
    0.40
    MLLoader
    0.39
    câ
    0.39
     suprême
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.