© 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. 6-RES-MATRYOSHKA-DC
    7. 1490
    Prev
    Next
    INDEX
    Explanations

    mentions of characters and the rules for naming variables in programming languages

    oai_token-act-pair · gemini-2.0-flash
    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
     AspNetCore
    -0.57
     Bist
    -0.51
     speciality
    -0.50
     jspb
    -0.47
     Phipps
    -0.47
     Doy
    -0.47
     précis
    -0.47
     JAK
    -0.47
    وصف
    -0.46
    Stub
    -0.46
    POSITIVE LOGITS
     letters
    1.27
    fromCharCode
    1.15
    letters
    1.08
    Letters
    1.08
     Letters
    1.06
     letter
    1.03
     lettres
    1.03
     LETTERS
    1.03
     Buchstaben
    0.98
    Letter
    0.94
    Activations Density 0.693%

    No Known Activations