© 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. 30760
    Prev
    Next
    INDEX
    Explanations

    references to prejudice or biased judgments in legal contexts

    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
    RenderAtEndOf
    -0.85
    LookAnd
    -0.75
     Stark
    -0.74
    SOUNDBITE
    -0.74
     Lohan
    -0.71
    OnAdd
    -0.71
    ❹
    -0.69
     Somerville
    -0.68
     Lw
    -0.68
    Stark
    -0.68
    POSITIVE LOGITS
     prejudice
    1.30
     Prejudice
    1.19
    judice
    1.16
     prejudices
    1.05
     prejudiced
    1.02
     prejud
    0.80
     prejudicial
    0.76
     preju
    0.71
     GIP
    0.68
     PMP
    0.67
    Activations Density 0.006%

    No Known Activations