© 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. 72713
    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
     Gass
    -0.54
     diplomat
    -0.54
    distingu
    -0.53
    kháu
    -0.51
    КИ
    -0.50
    ghest
    -0.50
    NEYS
    -0.50
     Galvan
    -0.50
    mati
    -0.50
    Reyn
    -0.49
    POSITIVE LOGITS
     beginnetje
    0.77
     autorytatywna
    0.59
     للاسماء
    0.56
    ApiModel
    0.52
    ViewImports
    0.50
     frattempo
    0.50
     disambiguazione
    0.50
     ""],
    0.49
     للمعارف
    0.48
    Bibliograf
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.