© 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. 1-RES-MATRYOSHKA-DC
    7. 1562
    Prev
    Next
    INDEX
    Explanations

    references to the action of making a precise or selective incision

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ThroughAttribute
    -0.86
    SequentialGroup
    -0.78
    setVerticalGroup
    -0.72
    Бахар
    -0.70
    ValueStyle
    -0.69
    ,:);
    -0.60
    phazard
    -0.60
     gynhyrchwyd
    -0.59
    PerformLayout
    -0.57
    complexContent
    -0.57
    POSITIVE LOGITS
     cut
    4.72
     Cut
    4.44
    cut
    4.38
    Cut
    4.34
     cuts
    4.22
     CUT
    4.13
     cutting
    4.03
    CUT
    4.03
     Cuts
    3.86
    cuts
    3.83
    Activations Density 0.192%

    No Known Activations