© 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. 2-RES-MATRYOSHKA-DC
    7. 2574
    Prev
    Next
    INDEX
    Explanations

    references to the concept of following established customs or conventions

    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
     frequent
    -0.73
    frequent
    -0.69
     frequently
    -0.66
    frequently
    -0.63
     Frequent
    -0.63
    Frequent
    -0.63
     متعلقه
    -0.61
     common
    -0.59
    Estar
    -0.57
    "");
    -0.56
    POSITIVE LOGITS
    Traditional
    2.97
     traditional
    2.95
     Traditional
    2.95
    traditional
    2.84
     traditionelle
    2.42
     tradi
    2.34
     traditionnelle
    2.28
     traditionellen
    2.28
     traditionnel
    2.25
     tradicional
    2.20
    Activations Density 0.013%

    No Known Activations