© 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. 0-RES-MATRYOSHKA-DC
    7. 11889
    Prev
    Next
    INDEX
    Explanations

    segments of text containing references to mathematical transformations or equations

    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
     McDaniel
    -0.63
     SR
    -0.60
    reibung
    -0.57
    writeByte
    -0.57
    kirch
    -0.56
     mellett
    -0.54
    ulico
    -0.54
     kasarigan
    -0.52
    はじめに
    -0.52
    urilor
    -0.52
    POSITIVE LOGITS
    sr
    2.66
     sr
    1.27
    IntoConstraints
    0.81
     FontWeight
    0.62
     MainAxisSize
    0.57
    tagHelper
    0.55
    ôi
    0.54
    Sr
    0.54
    winston
    0.53
     препратки
    0.53
    Activations Density 0.001%

    No Known Activations