© 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. 45138
    Prev
    Next
    INDEX
    Explanations

    predictors

    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
     predict
    -0.71
    xic
    -0.71
     predicting
    -0.70
    hr
    -0.65
    ed
    -0.62
     Levinson
    -0.62
    ored
    -0.60
    ckey
    -0.60
    et
    -0.59
    age
    -0.59
    POSITIVE LOGITS
    ⓧ
    0.64
    contentLoaded
    0.64
    "});
    0.63
    DoubleQuotes
    0.63
    ')";
    0.63
    };*/
    0.63
    はじめに
    0.62
    IContainer
    0.61
    )];
    
    0.60
    хьтан
    0.60
    Activations Density 0.089%

    No Known Activations