© 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. 75326
    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
    expandindo
    -0.73
    msgTypes
    -0.67
     Wicidata
    -0.64
     ModelExpression
    -0.62
    labus
    -0.59
     fieldNum
    -0.59
    enumii
    -0.57
    xase
    -0.56
     <=",
    -0.55
    yyj
    -0.54
    POSITIVE LOGITS
    FormTagHelper
    0.52
     st
    0.47
     Apart
    0.46
    KURZBESCHREIBUNG
    0.46
     chat
    0.44
    mlung
    0.44
     ser
    0.43
     Sterne
    0.42
    gen
    0.41
     EdgeInsets
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.