© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76061
    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
     متعلقه
    -0.61
     وتسجيلات
    -0.56
    WidgetItem
    -0.56
     tendenza
    -0.54
    principalTable
    -0.53
    StateException
    -0.52
     frères
    -0.51
     antaranya
    -0.50
     ModelExpression
    -0.50
     règle
    -0.50
    POSITIVE LOGITS
    ArrowToggle
    0.68
    Lähteet
    0.56
     typelib
    0.55
    ParallelGroup
    0.51
    ⓧ
    0.48
    馃
    0.47
     dry
    0.47
     solid
    0.46
    HSSF
    0.46
     חיצוניים
    0.45
    Activations Density 0.002%

    No Known Activations