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. 40862
    Prev
    Next
    INDEX
    Explanations

    technical processes

    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
    :✨
    -0.76
    addGap
    -0.75
     Roskov
    -0.75
    addCriterion
    -0.75
    TestingModule
    -0.75
    styleType
    -0.74
    ็จ
    -0.72
    клопе
    -0.72
    ReusableCell
    -0.72
    
    -0.72
    POSITIVE LOGITS
    ’
    0.79
    '
    0.75
    ↵↵
    0.69
    .
    0.67
    M
    0.63
    2
    0.62
    Z
    0.58
    Y
    0.57
    of
    0.57
     of
    0.56
    Activations Density 0.043%

    No Known Activations