© 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. 7673
    Prev
    Next
    INDEX
    Explanations

    the use of specific dollar sign patterns or notation related to code or variables

    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
     noDo
    -0.82
    */),
    -0.70
    ConstraintMaker
    -0.68
    */;
    -0.66
    OGND
    -0.66
     /\.
    -0.65
    FTFY
    -0.61
     onPostExecute
    -0.61
     horaire
    -0.61
     BorderSide
    -0.61
    POSITIVE LOGITS
    $
    0.60
    ::$
    0.56
    .$
    0.54
    XMLSchema
    0.53
    зь
    0.49
     ['$
    0.49
    Су
    0.49
    ByUsername
    0.49
     Bourgoin
    0.49
    ثيق
    0.49
    Activations Density 0.065%

    No Known Activations