© 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. 3-RES-MATRYOSHKA-DC
    7. 1990
    Prev
    Next
    INDEX
    Explanations

    the word "repeat" or variations of it, sometimes adjacent to words like "until", "loop", or other related words.

    oai_token-act-pair · gemini-2.0-flash
    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
    tinyos
    -0.63
    fstream
    -0.61
    arina
    -0.59
    enzio
    -0.59
    tehen
    -0.58
    fang
    -0.57
    ))/(
    -0.57
    فيات
    -0.57
    ,:),
    -0.55
    msen
    -0.54
    POSITIVE LOGITS
     repeat
    2.98
     repeats
    2.80
    repeat
    2.75
     Repeat
    2.75
     repeating
    2.67
    Repeat
    2.63
     repeated
    2.59
     Repe
    2.50
     repetition
    2.48
    REPEAT
    2.39
    Activations Density 0.403%

    No Known Activations