Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11056
    Prev
    Next
    INDEX
    Explanations

    workpiece

    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
    rope
    -0.57
     US
    -0.49
    span
    -0.47
    ie
    -0.47
    ia
    -0.47
    ty
    -0.47
    ...
    -0.45
     pro
    -0.45
     release
    -0.45
    rest
    -0.45
    POSITIVE LOGITS
    weetened
    0.70
    .")
    
    0.69
    ']))
    
    0.68
    ')";
    0.67
    ?>">
    0.66
    ";}
    0.65
     BoxFit
    0.65
    .")]
    0.65
    )|^{
    0.65
    %");
    0.64
    Activations Density 0.124%

    No Known Activations