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. 20-CLT-HP
    4. 74038
    Prev
    Next
    INDEX
    Explanations

    ).

    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
     lumineuse
    -0.56
    NamedQueries
    -0.52
     Gump
    -0.52
     Partagez
    -0.50
    "';
    -0.50
    alnız
    -0.49
     Gulf
    -0.48
     EconPapers
    -0.48
     Nunn
    -0.47
    copo
    -0.47
    POSITIVE LOGITS
     cref
    0.64
    ValueStyle
    0.54
    HtmlAttribute
    0.52
    спорти
    0.50
    onnaise
    0.49
     ATTR
    0.49
    nteral
    0.48
    editText
    0.47
     createState
    0.46
     ATR
    0.46
    Activations Density 0.000%

    No Known Activations