© 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. 1-CLT-HP
    7. 12284
    Prev
    Next
    INDEX
    Explanations

    -

    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
    D
    -0.43
    LOU
    -0.42
    K
    -0.41
    are
    -0.40
     a
    -0.40
    L
    -0.40
    emes
    -0.40
    M
    -0.38
    Arg
    -0.38
    Le
    -0.38
    POSITIVE LOGITS
     Administrativna
    0.60
    ς
    0.59
     Italijani
    0.56
    ItemBackground
    0.56
     ModelExpression
    0.54
    iddhar
    0.54
    cipar
    0.54
    клопе
    0.53
    WriteBarrier
    0.53
     Vitale
    0.53
    Activations Density 0.223%

    No Known Activations