© 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. 1359
    Prev
    Next
    INDEX
    Explanations

    references to the entire or complete thing

    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
     Total
    -1.03
    Total
    -1.00
     total
    -0.94
    total
    -0.91
     TOTAL
    -0.82
    TOTAL
    -0.69
     totaling
    -0.61
     للاسماء
    -0.60
    setTotal
    -0.58
     총
    -0.57
    POSITIVE LOGITS
     whole
    4.72
    whole
    4.53
    Whole
    4.09
     WHOLE
    3.86
     entire
    3.83
     Whole
    3.70
     Entire
    3.16
    entire
    3.06
     ENTIRE
    2.95
     ganze
    2.92
    Activations Density 0.044%

    No Known Activations