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. 0-CLT-HP
    4. 40813
    Prev
    Next
    INDEX
    Explanations

    important

    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
     pleaſure
    -0.86
     démocr
    -0.85
     autorytatywna
    -0.84
    LEncoder
    -0.81
     ſmall
    -0.79
     dirigeants
    -0.78
    SequentialGroup
    -0.77
    IVEREF
    -0.74
     مشين
    -0.73
    Autoritní
    -0.73
    POSITIVE LOGITS
     that
    0.74
     to
    0.69
    queryInterface
    0.46
     with
    0.42
     in
    0.41
    ,
    0.41
    matchCondition
    0.41
    ’
    0.41
    <bos>
    0.40
    ;
    0.40
    Activations Density 0.046%

    No Known Activations