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. 22-CLT-HP
    4. 74353
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · 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
    DockStyle
    -0.96
    DoubleQuotes
    -0.79
    setVerticalGroup
    -0.78
    Jeografia
    -0.72
    (!__
    -0.67
    GIVEREF
    -0.67
     المعيارى
    -0.66
    TagMode
    -0.66
    Collegamenti
    -0.65
    AsUp
    -0.65
    POSITIVE LOGITS
     closely
    0.51
     strongly
    0.50
     deeply
    0.46
    /[
    0.45
    скар
    0.45
    In
    0.45
     sincerely
    0.43
    Se
    0.41
    S
    0.40
     centers
    0.39
    Activations Density 0.002%

    No Known Activations