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. 11060
    Prev
    Next
    INDEX
    Explanations

    math or code

    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
     BoxFit
    -0.77
    phazard
    -0.75
    
    -0.73
     pleaſure
    -0.73
    });*/
    -0.72
     TextInputType
    -0.69
     OFDb
    -0.68
    脚注の使い方
    -0.66
    uminum
    -0.66
    %"),
    -0.65
    POSITIVE LOGITS
    .
    0.67
    '
    0.54
    ,
    0.49
    ’
    0.49
     
    0.48
    ID
    0.47
    :
    0.43
     distribution
    0.43
     -
    0.43
    袋
    0.42
    Activations Density 0.012%

    No Known Activations