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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14187
    Prev
    Next
    INDEX
    Explanations

    lines of code that import Java libraries or specific classes within those libraries

    oai_token-act-pair · gemini-2.0-flash

    semicolon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;
    -1.15
     ;
    -0.82
    );
    -0.76
    ";
    -0.75
    .;
    -0.70
    ,
    -0.69
    ;
    
    -0.69
    ();
    -0.68
    ;}
    -0.66
    $;
    -0.63
    POSITIVE LOGITS
     Efq
    1.19
     Houſe
    0.98
     esternos
    0.97
     Theſe
    0.95
     مشين
    0.95
    abestanden
    0.91
    ^(@)
    0.91
     initComponents
    0.90
     houſe
    0.89
     للاسماء
    0.88
    Activations Density 1.841%

    No Known Activations