© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92146
    Prev
    Next
    INDEX
    Explanations

    Providing

    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
    Providing
    -0.97
     Providing
    -0.78
    hman
    -0.58
    諧
    -0.55
     Its
    -0.52
     Usually
    -0.52
     forcé
    -0.51
     According
    -0.51
     essendo
    -0.51
     herself
    -0.50
    POSITIVE LOGITS
    )";
    
    0.72
    complexContent
    0.72
    elfare
    0.71
     BRARY
    0.69
    moiselle
    0.67
    +:+
    0.66
    OGND
    0.65
    esterday
    0.65
     ModelExpression
    0.65
    🏻‍♀️
    0.64
    Activations Density 0.181%

    No Known Activations