© 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. 1508
    Prev
    Next
    INDEX
    Explanations

    references to the racial term or concept "race," particularly in the context of discussing racism or racial issues

    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
     pember
    -0.52
     Lolita
    -0.52
     kaarangay
    -0.51
     Bridget
    -0.51
    Bridget
    -0.50
     Mem
    -0.50
     Imp
    -0.50
    tillon
    -0.50
    véni
    -0.49
    กล
    -0.49
    POSITIVE LOGITS
     ra
    2.83
    ra
    2.42
     Ra
    2.42
    Ra
    2.42
     RA
    2.38
    RA
    2.34
     Rac
    2.08
    Rac
    1.88
     rais
    1.68
     rake
    1.66
    Activations Density 0.470%

    No Known Activations