© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9175
    Prev
    Next
    INDEX
    Explanations

    racist

    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
     sexist
    -1.02
     sexism
    -0.97
    InvalidProtocol
    -0.61
    cemic
    -0.60
    racism
    -0.54
     homophobic
    -0.54
     racism
    -0.52
     racist
    -0.52
     BeautifulSoup
    -0.52
    racist
    -0.51
    POSITIVE LOGITS
    AccessorTable
    0.61
     صوتيه
    0.57
    ATURE
    0.55
     nawr
    0.55
     كمان
    0.54
     незавершена
    0.53
     kasarigan
    0.53
     autorytatywna
    0.52
    vacy
    0.52
    ing
    0.51
    Activations Density 0.003%

    No Known Activations