© 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. 3473
    Prev
    Next
    INDEX
    Explanations

    references to scholarly publications and research outputs related to scientific authorship, collaboration, and publications

    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
     تضيفلها
    -0.71
    AndEndTag
    -0.69
    "])){
    -0.66
    archiviato
    -0.65
    CompleteListener
    -0.65
     himſelf
    -0.62
     ſeveral
    -0.61
     Мексичка
    -0.60
    //});
    -0.60
    ppets
    -0.59
    POSITIVE LOGITS
    findpost
    0.59
    SBATCH
    0.54
    xdr
    0.54
     delegates
    0.50
     Delegate
    0.47
     Theses
    0.47
    minate
    0.46
     PPT
    0.46
    err
    0.46
     InputDecoration
    0.46
    Activations Density 0.695%

    No Known Activations