© 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. 2664
    Prev
    Next
    INDEX
    Explanations

    patterns of programming code snippets and mathematical notation

    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
    elo
    -0.51
    illett
    -0.50
     Boyer
    -0.50
    helo
    -0.49
    มอ
    -0.49
    idends
    -0.49
     [[
    -0.48
    weeted
    -0.48
     melu
    -0.48
     Herzog
    -0.47
    POSITIVE LOGITS
    (#
    2.44
    aarrggbb
    0.83
     Ephesus
    0.82
    bootstrapcdn
    0.79
    :✨
    0.78
     дописавши
    0.75
    #+#
    0.73
     InputDecoration
    0.69
    (___
    0.69
     cauſe
    0.69
    Activations Density 0.006%

    No Known Activations