© 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. 2-RES-MATRYOSHKA-DC
    7. 7493
    Prev
    Next
    INDEX
    Explanations

    references to mathematical or scientific articles, publications, and technical identifiers

    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
    COUVER
    -0.63
    posables
    -0.63
    VersionUID
    -0.60
    triple
    -0.60
    IntoConstraints
    -0.60
     Uptake
    -0.60
    ubscribe
    -0.59
     triple
    -0.57
    zeß
    -0.56
     AssemblyCulture
    -0.55
    POSITIVE LOGITS
    Gom
    0.60
    TagMode
    0.57
    devServer
    0.57
    ^{*}=
    0.54
     AssemblyTitle
    0.54
     Akismet
    0.53
    HM
    0.51
    sendFile
    0.51
     Pitman
    0.50
    ˏ
    0.50
    Activations Density 0.376%

    No Known Activations