© 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. 1-RES-MATRYOSHKA-DC
    7. 1473
    Prev
    Next
    INDEX
    Explanations

    references to white people or whiteness

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    )++;
    -0.68
    __':
    -0.67
    verifyException
    -0.65
    @[+][
    -0.64
    principalTable
    -0.62
    __":
    -0.62
    TagHelpers
    -0.60
    lofen
    -0.59
    homonymie
    -0.59
    })()
    -0.57
    POSITIVE LOGITS
     white
    4.59
    white
    4.31
     White
    4.28
    White
    4.28
     WHITE
    3.92
    WHITE
    3.69
     whites
    3.27
    白
    3.16
     weißen
    2.91
    whites
    2.88
    Activations Density 0.069%

    No Known Activations