© 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. 3354
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "and" in text

    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
    providedIn
    -0.76
     EconPapers
    -0.76
    AccessorTable
    -0.76
    Còn
    -0.71
     Efq
    -0.70
     autorytatywna
    -0.68
     ویکی‌پدیای
    -0.67
    GraphicsUnit
    -0.67
    RepeatedField
    -0.67
    Bibliograf
    -0.66
    POSITIVE LOGITS
    RegressionTest
    0.61
     perquè
    0.60
     deoarece
    0.52
    DoubleQuotes
    0.50
    ideae
    0.48
    Abp
    0.47
     faptul
    0.46
     poiché
    0.46
    HCR
    0.46
    \
    0.43
    Activations Density 1.111%

    No Known Activations