© 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. 2404
    Prev
    Next
    INDEX
    Explanations

    code snippets or strings containing specific quoted patterns, often related to configuration messages, debug messages, or code comments

    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
     vertes
    -0.53
    tirar
    -0.47
    ยม
    -0.45
    dataTable
    -0.44
     turi
    -0.43
     always
    -0.41
    actif
    -0.41
     nghiệp
    -0.40
     also
    -0.40
    ')->
    -0.40
    POSITIVE LOGITS
     ویکی‌پدیا
    1.00
    WebElementEntity
    0.99
    LookAnd
    0.95
    webElementXpaths
    0.93
     nakalista
    0.91
    tagHelperRunner
    0.85
     Exacts
    0.82
     صوتيه
    0.82
     للاسماء
    0.82
    awtextra
    0.81
    Activations Density 0.229%

    No Known Activations