© 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. 5-CLT-HP
    7. 92433
    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
     missione
    -0.56
    CURRENCY
    -0.56
     métallique
    -0.56
     käytet
    -0.54
    centiles
    -0.54
     perang
    -0.52
    TProtocol
    -0.52
    InputBorder
    -0.52
    AntiForgeryToken
    -0.52
     vendus
    -0.50
    POSITIVE LOGITS
    windowFixed
    0.63
    PerformLayout
    0.56
     asthma
    0.54
     colesterol
    0.50
     pneumonia
    0.50
     diarrhea
    0.50
     pregnant
    0.49
     rheumatic
    0.49
     placenta
    0.48
     pylori
    0.48
    Activations Density 0.000%

    No Known Activations