© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6245
    Prev
    Next
    INDEX
    Explanations

    prejudice and terrorism

    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
    Negative Logits
    脚注の使い方
    -0.57
    Semitism
    -0.53
    :+:
    -0.52
    semitism
    -0.51
    craper
    -0.50
    ORPG
    -0.50
    requireNonNull
    -0.48
    CloseOperation
    -0.48
    etor
    -0.48
    classnames
    -0.48
    POSITIVE LOGITS
     Indexing
    0.54
     Index
    0.52
    DIPSETTING
    0.52
     purtroppo
    0.50
    κολου
    0.49
    Aholisi
    0.49
    EXPERIENCE
    0.48
     Roskov
    0.48
     nakalista
    0.48
     unfortunately
    0.48
    Activations Density 0.002%

    No Known Activations