© 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. 4101
    Prev
    Next
    INDEX
    Explanations

    references to programming languages, especially the term "programming."

    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
     code
    -0.97
     Code
    -0.93
    code
    -0.84
    Code
    -0.82
    CODE
    -0.80
     CODE
    -0.78
     código
    -0.78
     Codes
    -0.69
    コード
    -0.68
     codes
    -0.68
    POSITIVE LOGITS
     programming
    3.31
     Programming
    3.11
    programming
    2.97
    Programming
    2.94
     programmer
    2.16
     programmation
    2.13
     programmers
    2.03
     programmed
    1.97
     Programmer
    1.93
     programación
    1.86
    Activations Density 0.007%

    No Known Activations