© 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. 1348
    Prev
    Next
    INDEX
    Explanations

    references to official or authoritative sources

    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
    +:+
    -0.75
    TRIBUT
    -0.63
     utafitiHapana
    -0.63
    abestanden
    -0.61
    dbury
    -0.60
    issauga
    -0.58
     skak
    -0.56
    ContentAsync
    -0.54
     ubic
    -0.54
    ãng
    -0.54
    POSITIVE LOGITS
     official
    4.09
     Official
    3.67
    official
    3.67
    Official
    3.67
     OFFICIAL
    3.53
    OFFICIAL
    3.28
     oficial
    3.05
     officially
    3.02
     formal
    2.72
     officiel
    2.70
    Activations Density 0.317%

    No Known Activations