Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91518
    Prev
    Next
    INDEX
    Explanations

    firm

    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
    tagHelperRunner
    -1.23
    findpost
    -1.02
    OGND
    -1.00
    ConstraintMaker
    -1.00
     تضيفلها
    -0.98
    AndEndTag
    -0.95
    IsMutable
    -0.95
    SourceChecksum
    -0.95
    WebElementEntity
    -0.93
     للاسماء
    -0.93
    POSITIVE LOGITS
    ↵↵
    0.59
    ’
    0.52
     /
    0.47
    /
    0.43
    newInstance
    0.43
    '
    0.42
    هی
    0.41
    makedirs
    0.40
    ing
    0.40
    /.
    0.39
    Activations Density 0.451%

    No Known Activations