© 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. 3110
    Prev
    Next
    INDEX
    Explanations

    references to mathematical concepts related to advanced algebra, topology, and functional analysis

    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
    ագրություններ
    -0.76
    AutoresizingMask
    -0.75
    ThroughAttribute
    -0.73
    adaptiveStyles
    -0.71
    verwijspagina
    -0.70
    RectangleBorder
    -0.69
    ."+
    -0.67
    duled
    -0.65
    CppCodeGen
    -0.65
    oneofs
    -0.64
    POSITIVE LOGITS
    asztal
    0.52
     where
    0.47
    inari
    0.46
    zeka
    0.46
    би
    0.45
    RequestParam
    0.42
    Demografia
    0.41
    val
    0.40
    ǒ
    0.39
    makeText
    0.39
    Activations Density 0.100%

    No Known Activations