© 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. 5-CLT-HP
    7. 1023
    Prev
    Next
    INDEX
    Explanations

    comparisons

    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
     Universitaria
    -0.44
     
    -0.43
    autoIncrement
    -0.41
    ék
    -0.41
     we
    -0.41
    ukone
    -0.40
    وانی
    -0.39
     riscal
    -0.39
     they
    -0.39
    skri
    -0.39
    POSITIVE LOGITS
     للمعارف
    0.82
    dafx
    0.75
    ScopeManager
    0.75
    #+#
    0.75
    "])
    0.72
     EconPapers
    0.70
     שוליים
    0.69
    )"),
    0.68
     мәкал
    0.68
    }")
    0.68
    Activations Density 0.001%

    No Known Activations