© 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. 20-CLT-HP
    7. 72996
    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
     resourceCulture
    -0.90
    httphttps
    -0.86
     Chwiliwch
    -0.77
    EDEFAULT
    -0.74
    ValueGeneration
    -0.74
    sidemargin
    -0.73
    sizeCache
    -0.70
     Wicidata
    -0.69
    出版年
    -0.69
    RectangleBorder
    -0.69
    POSITIVE LOGITS
     
    0.76
    oly
    0.48
    lear
    0.44
    lyser
    0.44
    ')['
    0.44
    γά
    0.44
    labili
    0.43
    कर
    0.43
     saints
    0.43
    花板
    0.41
    Activations Density 0.000%

    No Known Activations