© 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. 1463
    Prev
    Next
    INDEX
    Explanations

    references to programming language constructs and code elements such as classes, methods, variables, and data types

    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
    string
    -0.93
     string
    -0.72
    array
    -0.66
     array
    -0.63
     ReSharper
    -0.61
     ainfi
    -0.59
     opérateur
    -0.52
    cout
    -0.50
    list
    -0.50
     autorytatywna
    -0.50
    POSITIVE LOGITS
    String
    2.19
     String
    2.09
    Integer
    1.29
    Object
    1.25
     Integer
    1.25
     Object
    1.07
    Boolean
    1.05
    Double
    1.01
    Float
    1.01
     Boolean
    0.94
    Activations Density 0.433%

    No Known Activations