© 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. 77408
    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
     ModelExpression
    -0.71
     mergeFrom
    -0.71
     Aircraft
    -0.70
    UnusedPrivate
    -0.69
    CopyWith
    -0.68
    Engineers
    -0.68
    jspx
    -0.66
    Geology
    -0.65
     Geological
    -0.65
    urcht
    -0.64
    POSITIVE LOGITS
     early
    0.52
    early
    0.48
     vroe
    0.43
    出版年
    0.41
     član
    0.39
     earl
    0.39
     recibirá
    0.37
    manjaro
    0.36
     llego
    0.35
     vroeger
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.