© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1561
    Prev
    Next
    INDEX
    Explanations

    mentions of specific loop structures within proteins

    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
    Negative Logits
     round
    -0.79
     Round
    -0.79
    round
    -0.75
    Round
    -0.75
     numberWith
    -0.69
     ROUND
    -0.66
     rounded
    -0.62
     rounding
    -0.62
    rounded
    -0.62
     Rober
    -0.60
    POSITIVE LOGITS
     loop
    4.69
    loop
    4.25
     Loop
    4.09
     loops
    4.03
    Loop
    3.86
     LOOP
    3.59
     Loops
    3.53
    loops
    3.30
    LOOP
    3.14
     looping
    3.02
    Activations Density 0.036%

    No Known Activations