© 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. 77016
    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
     parseFrom
    -0.68
    OfWork
    -0.68
    帖最后由
    -0.64
     termica
    -0.61
     Taktlose
    -0.61
    tentu
    -0.60
     ConstraintSet
    -0.60
     élevées
    -0.60
    MigrationBuilder
    -0.58
     spesa
    -0.57
    POSITIVE LOGITS
     means
    0.42
    URCH
    0.40
    urch
    0.40
     ddelweddau
    0.39
    Ế
    0.39
     reasoned
    0.39
    crip
    0.39
    brale
    0.38
     sto
    0.37
     averaged
    0.37
    Activations Density 0.003%

    No Known Activations