© 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. 643
    Prev
    Next
    INDEX
    Explanations

    specific patterns of complex mathematical notation and symbols

    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
    {
    -0.69
    DataURL
    -0.68
    <eos>
    -0.62
    {#
    -0.56
     surla
    -0.56
    er
    -0.55
     تضيفلها
    -0.55
    RegressionTest
    -0.54
    _{
    -0.53
    richTextPanel
    -0.53
    POSITIVE LOGITS
     Geraadpleegd
    0.69
    moiselle
    0.65
    nexpected
    0.64
     Réponses
    0.62
    NUMX
    0.61
    Gambas
    0.60
     ――――
    0.60
     réflex
    0.60
     '\\;'
    0.59
    rouvez
    0.59
    Activations Density 5.670%

    No Known Activations