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. 40909
    Prev
    Next
    INDEX
    Explanations

    of

    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
     يتيمه
    -0.83
    TagMode
    -0.82
     Wikimedijinoj
    -0.79
     <>",
    -0.79
     ویکی‌پدیای
    -0.79
    
    -0.79
    ContentAsync
    -0.77
    getDescriptor
    -0.76
    ///</
    -0.74
     snippetHide
    -0.73
    POSITIVE LOGITS
     a
    0.85
     the
    0.76
     an
    0.74
     your
    0.73
     any
    0.63
     yourself
    0.54
     ra
    0.51
    ,
    0.51
    ↵↵
    0.50
     our
    0.50
    Activations Density 0.552%

    No Known Activations