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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 364
    Prev
    Next
    INDEX
    Explanations

    references to mathematical concepts and specific technical terminology

    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
    rąg
    -0.50
     Chriftian
    -0.49
     occaf
    -0.48
    For
    -0.47
    Whilst
    -0.47
     henne
    -0.46
    In
    -0.44
     Jefus
    -0.44
    Of
    -0.44
     jepang
    -0.44
    POSITIVE LOGITS
    脚注の使い方
    1.02
     nahilalakip
    0.99
    enumi
    0.88
    /***/
    0.86
    THE
    0.86
    tagHelperRunner
    0.83
    ]--;
    0.83
    +:+
    0.82
     THE
    0.77
     مشين
    0.75
    Activations Density 4.776%

    No Known Activations