© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1453
    Prev
    Next
    INDEX
    Explanations

    references to mathematical objects involved in advanced concepts of topology, algebra, and 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
    Negative Logits
     nakalista
    -0.65
    StoreMessageInfo
    -0.63
     addSubview
    -0.52
    üyor
    -0.50
    бочка
    -0.50
    ."+
    -0.48
    theon
    -0.47
    rej
    -0.46
    memcpy
    -0.46
     kony
    -0.46
    POSITIVE LOGITS
    AndEndTag
    0.78
     kasarigan
    0.68
    Identyfik
    0.66
    featureID
    0.65
     internetowa
    0.62
    StoryboardSegue
    0.62
    MigrationBuilder
    0.60
     "..\..\..\
    0.59
     Administrativna
    0.58
     belonging
    0.57
    Activations Density 2.784%

    No Known Activations