© 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. 2-RES-MATRYOSHKA-DC
    7. 5581
    Prev
    Next
    INDEX
    Explanations

    numerical subtraction expressions

    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
     ſhe
    -0.74
     beſ
    -0.73
    RegressionTest
    -0.71
     viſ
    -0.70
     uſ
    -0.69
     ſta
    -0.69
     contextLoads
    -0.68
     -
    -0.68
     ſeveral
    -0.68
     raiſ
    -0.67
    POSITIVE LOGITS
    Bronnen
    0.62
    稲田
    0.61
    ƒ
    0.61
     مشين
    0.58
    ‘
    0.58
    WriteTagHelper
    0.57
    ecu
    0.57
    Referenties
    0.57
     defecto
    0.56
    aragua
    0.55
    Activations Density 0.106%

    No Known Activations