© 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. 3738
    Prev
    Next
    INDEX
    Explanations

    calculations related to division and computing remainders

    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
     Split
    -1.41
     splitting
    -1.39
     split
    -1.36
    split
    -1.33
     splits
    -1.33
    Split
    -1.29
    splitting
    -1.27
    SPLIT
    -1.09
    splits
    -1.08
    plit
    -0.98
    POSITIVE LOGITS
    <!--[
    0.55
     rien
    0.52
     hivat
    0.50
    >");
    0.49
    ện
    0.49
    ?></
    0.48
     QtGui
    0.47
    eqn
    0.47
     tangki
    0.47
     köl
    0.46
    Activations Density 0.008%

    No Known Activations