© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45235
    Prev
    Next
    INDEX
    Explanations

    impropri

    np_max-act · gemini-2.0-flash
    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
     financières
    -0.81
     fondament
    -0.81
     énergé
    -0.80
     grecque
    -0.78
     européennes
    -0.77
     financière
    -0.74
    rawDesc
    -0.73
     chré
    -0.72
     dentaire
    -0.72
     vectorielles
    -0.72
    POSITIVE LOGITS
     >=",
    0.56
     ExecuteAsync
    0.52
    e
    0.51
    ability
    0.49
    }-${
    0.48
    URIComponent
    0.47
     plu
    0.47
    UnusedPrivate
    0.46
    NAH
    0.46
     Auto
    0.46
    Activations Density 0.520%

    No Known Activations