© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4498
    Prev
    Next
    INDEX
    Explanations

    Code/technical text

    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
     ")";
    -0.46
    bilities
    -0.43
    lists
    -0.43
    t
    -0.42
    books
    -0.42
    men
    -0.41
     OMITBAD
    -0.41
    findpost
    -0.41
    Board
    -0.40
    boards
    -0.40
    POSITIVE LOGITS
     MainAxisSize
    0.83
    
    0.69
    parsedMessage
    0.67
    ftagPool
    0.65
     UIFont
    0.64
     CGPoint
    0.62
    extField
    0.62
    interopRequire
    0.61
    NameValuePair
    0.61
    CastException
    0.60
    Activations Density 0.001%

    No Known Activations