© 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. 1043
    Prev
    Next
    INDEX
    Explanations

    transform

    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
     transform
    -0.81
     transforms
    -0.71
    functional
    -0.68
     relatively
    -0.64
     transformed
    -0.57
     functional
    -0.54
    time
    -0.54
     transformation
    -0.53
     Relatively
    -0.53
     transforma
    -0.50
    POSITIVE LOGITS
    tagHelperRunner
    1.02
    tvguidetime
    0.97
     كومونز
    0.91
    RegressionTest
    0.88
    Datuak
    0.87
    __*/
    0.85
    complexContent
    0.84
     تضيفلها
    0.84
    mybatisplus
    0.82
     Efq
    0.80
    Activations Density 0.108%

    No Known Activations