© 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. 1-RES-MATRYOSHKA-DC
    7. 989
    Prev
    Next
    INDEX
    Explanations

    references to repeated occurrence or timing, specifically the concept of **"once"** indicating an event happening a single time or a particular point in time

    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
     Chwiliwch
    -0.67
    rungsseite
    -0.66
    спонд
    -0.61
     Roskov
    -0.58
    saraba
    -0.57
    angos
    -0.57
     wikipagina
    -0.54
    aspectj
    -0.52
     المعيارى
    -0.52
    eabouts
    -0.52
    POSITIVE LOGITS
     once
    4.78
    once
    4.38
    Once
    4.13
     Once
    4.09
     ONCE
    3.91
    ONCE
    3.58
     einmal
    2.27
    一旦
    1.93
     مرة
    1.84
    一度
    1.77
    Activations Density 0.130%

    No Known Activations