© 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. 30849
    Prev
    Next
    INDEX
    Explanations

    statements that quantify or compare groups, particularly in discussions around race or social issues

    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
    +#+#
    -0.94
     مشين
    -0.91
     createState
    -0.87
    JspWriter
    -0.84
     ―――――
    -0.77
    withIdentifier
    -0.77
    цездатний
    -0.76
    клопе
    -0.76
     doInBackground
    -0.76
     мәкал
    -0.74
    POSITIVE LOGITS
    COL
    0.59
    addContainerGap
    0.55
    kha
    0.53
     ra
    0.51
     Col
    0.50
     COL
    0.47
     ./
    0.47
     fortunately
    0.47
     col
    0.47
    辞典
    0.46
    Activations Density 0.008%

    No Known Activations