© 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. 4358
    Prev
    Next
    INDEX
    Explanations

    references to iteration constructs in code

    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
     loop
    -0.71
    发表于
    -0.71
    metz
    -0.68
     Efq
    -0.66
     purpoſe
    -0.62
     organiser
    -0.60
     myſelf
    -0.60
    XtraGrid
    -0.59
     Megal
    -0.58
     وتسجيلات
    -0.58
    POSITIVE LOGITS
     iter
    2.45
     Iter
    2.39
    Iter
    2.31
    iter
    2.13
     iterative
    1.93
     iterate
    1.88
    ITER
    1.87
     iteration
    1.84
     iterations
    1.73
     Iteration
    1.68
    Activations Density 0.020%

    No Known Activations