© 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. 3514
    Prev
    Next
    INDEX
    Explanations

    mathematical computations

    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
     does
    -0.77
     is
    -0.71
     follows
    -0.66
    alities
    -0.66
    oredCriteria
    -0.65
     comes
    -0.65
    principalColumn
    -0.63
     isn
    -0.63
     makes
    -0.62
     doesn
    -0.62
    POSITIVE LOGITS
     igjen
    0.53
     ModelExpression
    0.50
     intptr
    0.49
     touristes
    0.48
     للاسماء
    0.47
     متعلقه
    0.44
     inconvénients
    0.43
     devenus
    0.43
     setTotal
    0.43
     again
    0.42
    Activations Density 0.029%

    No Known Activations