© 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. 91411
    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
    IsContent
    -0.62
     سكانية
    -0.55
    MIDDLEWARE
    -0.55
     sóc
    -0.53
    PMailer
    -0.52
    gameserver
    -0.52
     calendriers
    -0.51
    ouage
    -0.49
    nemouth
    -0.49
    extAlignment
    -0.49
    POSITIVE LOGITS
    GraphicsUnit
    0.69
    XmlAccessorType
    0.64
    DoubleQuotes
    0.61
    InSection
    0.61
    seamnă
    0.57
    rizona
    0.56
     Tarn
    0.54
    ươi
    0.53
     millón
    0.52
     spesa
    0.50
    Activations Density 0.000%

    No Known Activations