© 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. 73084
    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
    EndGlobalSection
    -0.77
    mybatisplus
    -0.68
    Diwedd
    -0.65
    saraba
    -0.62
    :✨
    -0.62
    RepeatedField
    -0.60
     EconPapers
    -0.59
    wußt
    -0.59
     unknownFields
    -0.59
    pushFollow
    -0.59
    POSITIVE LOGITS
     trasporto
    0.52
     mó
    0.50
     atribu
    0.48
     setting
    0.47
     over
    0.47
     SETTING
    0.45
     motion
    0.45
     transportasi
    0.45
     Motion
    0.45
    QQ
    0.45
    Activations Density 0.000%

    No Known Activations