© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74732
    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
    parsedMessage
    -0.75
    windowFixed
    -0.74
     autorytatywna
    -0.73
    RUnlock
    -0.69
    addCriterion
    -0.66
    OGND
    -0.65
     intptr
    -0.63
    FunctionFlags
    -0.61
    первых
    -0.60
    Personendaten
    -0.60
    POSITIVE LOGITS
     brancas
    0.57
     vermelhas
    0.54
     GoogleFonts
    0.53
     rosse
    0.50
     commerciali
    0.50
     gravidanza
    0.48
     carreaux
    0.48
     laikā
    0.47
    ondi
    0.47
     acrylique
    0.47
    Activations Density 0.002%

    No Known Activations