© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15553
    Prev
    Next
    INDEX
    Explanations

    scientific and mathematical expressions related to derivatives, schemes, and theoretical results

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.88
    unehmen
    -0.82
     myſelf
    -0.80
     purpoſe
    -0.79
     viſ
    -0.77
     fubject
    -0.76
     ſever
    -0.75
     Conſ
    -0.75
    protoimpl
    -0.74
    AccessorTable
    -0.74
    POSITIVE LOGITS
     prevision
    0.50
     Вікіпе
    0.50
    ్
    0.49
     نسخة
    0.49
     forma
    0.48
    Tikang
    0.48
     же
    0.47
    ്
    0.47
    seda
    0.46
     leves
    0.46
    Activations Density 0.038%

    No Known Activations