© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12268
    Prev
    Next
    INDEX
    Explanations

    law

    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
    ViewFeatures
    -0.54
    RegressionTest
    -0.51
    pirazione
    -0.49
    ItemBackground
    -0.48
    yatı
    -0.47
    Sortie
    -0.46
    Ethnicity
    -0.46
    eventbus
    -0.46
    pagnol
    -0.45
    WHM
    -0.45
    POSITIVE LOGITS
    ns
    0.54
    dy
    0.53
    dog
    0.52
    hand
    0.52
    man
    0.51
     cães
    0.51
    GEBURTSDATUM
    0.50
     cão
    0.49
    ny
    0.49
     enforce
    0.49
    Activations Density 0.002%

    No Known Activations