© 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. 72293
    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
    rawDesc
    -0.53
     DBNull
    -0.53
    WriteLiteral
    -0.52
     متعلقه
    -0.52
    ])));
    -0.50
     basic
    -0.48
    __':
    -0.48
    __":
    -0.48
    bindParam
    -0.47
    SequentialGroup
    -0.47
    POSITIVE LOGITS
     segar
    0.58
    PREFIX
    0.55
     common
    0.55
    ELING
    0.52
    common
    0.51
     communs
    0.51
    idah
    0.50
     commonplace
    0.50
     enfans
    0.50
    jewództ
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.