© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4794
    Prev
    Next
    INDEX
    Explanations

    instances of a specific mathematical symbol or format typically used in formal mathematical expressions or typesetting

    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
    vex
    -0.59
    UserScript
    -0.58
    onghi
    -0.56
     elé
    -0.55
    Externí
    -0.55
    endgroup
    -0.55
     Cowan
    -0.54
    wußt
    -0.53
     Baumann
    -0.52
    wyk
    -0.52
    POSITIVE LOGITS
    mathfrak
    3.19
    frak
    1.35
     متعلقه
    0.79
    rungsseite
    0.77
     صوتيه
    0.76
     HasFactory
    0.76
    Geplaatst
    0.73
    ChildScrollView
    0.70
     imageNamed
    0.69
    setVerticalGroup
    0.68
    Activations Density 0.014%

    No Known Activations