© 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. 18857
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting related to commas in text

    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
     tek
    -0.60
    en
    -0.55
    esh
    -0.55
    hit
    -0.53
     تک
    -0.51
     сту
    -0.51
    a
    -0.51
     beit
    -0.50
    rad
    -0.49
     contrario
    -0.48
    POSITIVE LOGITS
     للاسماء
    1.08
    (',',
    1.01
    Comma
    1.00
     commas
    0.96
     comma
    0.95
    comma
    0.95
    ,',
    0.90
    (',');
    0.90
    CloseOperation
    0.88
     (,
    0.83
    Activations Density 0.008%

    No Known Activations