© 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. 44101
    Prev
    Next
    INDEX
    Explanations

    dual

    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
     dual
    -1.08
     double
    -0.93
     Dual
    -0.89
     China
    -0.82
    Dual
    -0.82
     Double
    -0.81
    dual
    -0.76
    double
    -0.73
     DUAL
    -0.66
    Double
    -0.66
    POSITIVE LOGITS
     متعلقه
    1.07
     itſelf
    0.92
    脚注の使い方
    0.91
    \{\\
    0.87
     myſelf
    0.86
    évaluateur
    0.83
     purpoſe
    0.83
     nahilalakip
    0.78
    ScopeManager
    0.77
     himſelf
    0.76
    Activations Density 0.174%

    No Known Activations