© 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
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 7014
    Prev
    Next
    INDEX
    Explanations

    specific code or programming-related tokens, especially those associated with code comments, annotations, or references

    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
    niająca
    -0.57
    ագրություններ
    -0.56
     confidentialité
    -0.53
    וויק
    -0.53
    Osob
    -0.51
    цездатний
    -0.50
    homonymie
    -0.48
    ГЛА
    -0.48
     ate
    -0.47
     Advanced
    -0.47
    POSITIVE LOGITS
     })
    
    0.74
    IsContent
    0.72
     XCTest
    0.69
     كومونز
    0.65
    xim
    0.64
    허
    0.58
    ?}",
    0.57
     getUsername
    0.57
     Kości
    0.56
    ]){
    
    0.54
    Activations Density 0.895%

    No Known Activations