© 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. 1438
    Prev
    Next
    INDEX
    Explanations

    specific code structure elements or syntax keywords related to defining constants and configuring GUI components

    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
     snippetHide
    -0.67
     enfin
    -0.66
    finally
    -0.65
     наконец
    -0.65
    basicConfig
    -0.61
    Meanwhile
    -0.60
     Meanwhile
    -0.58
    rungsseite
    -0.58
    agang
    -0.56
    はじめに
    -0.56
    POSITIVE LOGITS
     final
    4.03
    final
    3.80
    Final
    3.58
     Final
    3.48
     FINAL
    3.23
    FINAL
    3.11
     finals
    2.28
    finals
    2.05
     finais
    1.99
     finale
    1.97
    Activations Density 0.219%

    No Known Activations