© 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. 4-CLT-HP
    7. 3364
    Prev
    Next
    INDEX
    Explanations

    code questions

    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
     spec
    -0.42
    Vielleicht
    -0.42
    Instead
    -0.41
     fær
    -0.41
    spec
    -0.40
     dizer
    -0.39
    Or
    -0.38
     invece
    -0.38
     Or
    -0.38
    ound
    -0.38
    POSITIVE LOGITS
     Réponses
    0.91
     ComVisible
    0.88
     oprot
    0.88
    DispatchToProps
    0.87
    thâu
    0.78
     بيها
    0.77
    Personensuche
    0.75
    HideFlags
    0.74
     &___
    0.73
     noqa
    0.73
    Activations Density 0.013%

    No Known Activations