© 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. 12-RES-MATRYOSHKA-DC
    7. 17166
    Prev
    Next
    INDEX
    Explanations

    references to racial or ethnic identities and diversity among groups

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     EconPapers
    -0.93
     surla
    -0.81
     StatefulWidget
    -0.81
    Tembelea
    -0.72
     ligiloj
    -0.71
     autorytatywna
    -0.68
     StatelessWidget
    -0.68
    protoimpl
    -0.66
    mybatisplus
    -0.64
     nakalista
    -0.63
    POSITIVE LOGITS
     ethnicity
    0.60
     Ethnicity
    0.56
     ethnic
    0.54
     Ethnic
    0.52
     rendition
    0.47
     iconFacebook
    0.47
    ticulate
    0.47
     difer
    0.46
     cautions
    0.46
     stucco
    0.46
    Activations Density 0.053%

    No Known Activations