© 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. 2-RES-MATRYOSHKA-DC
    7. 4170
    Prev
    Next
    INDEX
    Explanations

    references to mathematical notation, symbols, or formulas

    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
    i
    -0.59
     članak
    -0.56
     noqa
    -0.54
     Rog
    -0.53
    mbio
    -0.52
    例文帳に追加
    -0.52
    setContentType
    -0.51
     trụ
    -0.51
    loaf
    -0.50
    {
    -0.50
    POSITIVE LOGITS
    {$
    1.72
    {$\
    1.55
     {$
    1.36
    }{$
    1.33
    }{$\
    1.30
     {$\
    0.88
    ){$
    0.86
     poffe
    0.81
    ){$\
    0.79
     becauſe
    0.76
    Activations Density 0.019%

    No Known Activations