© 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. 503
    Prev
    Next
    INDEX
    Explanations

    she

    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
    elemField
    -0.80
     Fractions
    -0.73
     Fraction
    -0.73
    ]--;
    -0.71
    StructEnd
    -0.71
     fractions
    -0.70
     Normdatei
    -0.69
     fractionation
    -0.69
    ')):
    -0.68
    prefixer
    -0.66
    POSITIVE LOGITS
    stoy
    0.48
    sing
    0.47
     tornare
    0.46
    ual
    0.44
     quartiers
    0.44
     nouve
    0.44
    subj
    0.43
     Hallen
    0.42
    sym
    0.41
    AlterField
    0.40
    Activations Density 0.292%

    No Known Activations