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. 40790
    Prev
    Next
    INDEX
    Explanations

    shows

    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
    Portale
    -0.80
    ArrowToggle
    -0.75
    ⓧ
    -0.73
    ItemBackground
    -0.68
     समीक्षक
    -0.67
    Abitanti
    -0.65
     ddelweddau
    -0.64
    AsUp
    -0.63
    zzleHttp
    -0.62
    Viitteet
    -0.60
    POSITIVE LOGITS
     a
    0.97
     the
    0.89
     an
    0.85
     you
    0.79
    richTextPanel
    0.63
     all
    0.61
     what
    0.59
     two
    0.58
     three
    0.53
    neté
    0.53
    Activations Density 0.652%

    No Known Activations