© 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. 2-RES-MATRYOSHKA-DC
    7. 6958
    Prev
    Next
    INDEX
    Explanations

    code snippets related to including header files and preprocessor directives

    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
     devil
    -0.57
    ('.
    -0.56
     Colomb
    -0.53
     baga
    -0.53
    ittin
    -0.52
    JKLM
    -0.51
    hrer
    -0.51
    の高い
    -0.50
     cher
    -0.50
     doute
    -0.50
    POSITIVE LOGITS
    ViewImports
    0.90
    ngdoc
    0.77
     StatefulWidget
    0.73
    AndroidJUnit
    0.72
     linkovi
    0.67
    出版年
    0.66
     Normdatei
    0.66
    expandindo
    0.66
    BufferException
    0.65
     EconPapers
    0.64
    Activations Density 0.140%

    No Known Activations