© 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. 15669
    Prev
    Next
    INDEX
    Explanations

    references to race and ethnicity

    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
    rief
    -0.71
    intenance
    -0.69
    ISTRATION
    -0.69
    المناصب
    -0.68
    chaften
    -0.68
    +#+
    -0.66
    KELEY
    -0.66
    tanleria
    -0.66
     Paglinawan
    -0.66
    NOST
    -0.65
    POSITIVE LOGITS
     HttpHeaders
    0.44
    penup
    0.42
     ingenieros
    0.42
    abestanden
    0.41
     střed
    0.40
    DR
    0.40
     convenio
    0.38
     inš
    0.38
     kvinna
    0.37
    Member
    0.36
    Activations Density 0.157%

    No Known Activations