© 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. 21157
    Prev
    Next
    INDEX
    Explanations

    code elements and special characters used in programming or markup languages

    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
     kasarigan
    -0.94
    XMLSchema
    -0.61
    therners
    -0.56
     verwijzen
    -0.54
     lays
    -0.52
    Література
    -0.51
    省市镇
    -0.51
    FormTagHelper
    -0.50
    帖最后由
    -0.50
    inflater
    -0.50
    POSITIVE LOGITS
    PreferredItem
    0.77
     fédé
    0.71
    feinander
    0.59
    '];
    0.57
    XtraBars
    0.57
     présidentielle
    0.57
    ,:);
    0.57
    StructEnd
    0.57
     disponibilità
    0.56
     sérieux
    0.56
    Activations Density 0.261%

    No Known Activations