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. 1-CLT-HP
    4. 12861
    Prev
    Next
    INDEX
    Explanations

    source code/legal docs

    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
    ↵
    -0.82
     well
    -0.63
     single
    -0.56
     great
    -0.54
     good
    -0.54
     big
    -0.54
     successful
    -0.53
     first
    -0.52
     fast
    -0.52
     their
    -0.50
    POSITIVE LOGITS
    SharedDtor
    0.82
    OrNil
    0.78
     Italijanski
    0.75
     للاسماء
    0.71
    HtmlAttribute
    0.68
    DockStyle
    0.68
     للمعارف
    0.67
    __(/*!
    0.66
    AndEndTag
    0.66
    ">//
    0.66
    Activations Density 0.297%

    No Known Activations