© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14963
    Prev
    Next
    INDEX
    Explanations

    patterns indicating steady, ongoing change or progression

    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
    GraphicsUnit
    -0.54
    //:
    -0.54
     EdgeInsets
    -0.53
    LookAnd
    -0.52
    +#+
    -0.52
    MOQ
    -0.52
     ویکی‌پدیا
    -0.52
     recomendamos
    -0.51
    Rcpp
    -0.51
     ['./
    -0.50
    POSITIVE LOGITS
     steadily
    1.73
    holm
    1.02
     asymptotically
    0.68
    orianCalendar
    0.66
    ніципа
    0.61
     SearchView
    0.60
    holms
    0.58
     useAppContext
    0.58
    basicConfig
    0.57
    istoitu
    0.56
    Activations Density 0.001%

    No Known Activations