© 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. 0-CLT-HP
    7. 39898
    Prev
    Next
    INDEX
    Explanations

    golden

    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
    golden
    -1.13
    Golden
    -1.12
     golden
    -1.10
     Golden
    -1.04
    s
    -0.98
     GOLDEN
    -0.86
     mauvaises
    -0.68
     peores
    -0.68
    sti
    -0.67
    ів
    -0.66
    POSITIVE LOGITS
    +#+#
    0.71
     Normdatei
    0.70
     otomatig
    0.63
     sumpay
    0.60
    tagHelperRunner
    0.59
    HasAnnotation
    0.59
    pidou
    0.59
     فريبيس
    0.58
    writeField
    0.58
    PasswordEncoder
    0.56
    Activations Density 1.158%

    No Known Activations