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. 74240
    Prev
    Next
    INDEX
    Explanations

    at

    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
     defaultstate
    -0.67
    хьтан
    -0.62
    RenderAtEndOf
    -0.57
    IsContent
    -0.52
    Externí
    -0.52
     uby
    -0.50
     Abonnez
    -0.50
    )");
    
    -0.50
     CORPOR
    -0.49
    initComponents
    -0.49
    POSITIVE LOGITS
     per
    0.77
    Per
    0.65
     Per
    0.64
    per
    0.57
    mphony
    0.56
    bitkan
    0.55
    ########.
    0.54
    ::_('
    0.54
     الاطلاع
    0.52
    cinfo
    0.52
    Activations Density 0.046%

    No Known Activations