© 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. 2-RES-MATRYOSHKA-DC
    7. 5653
    Prev
    Next
    INDEX
    Explanations

    patterns related to the structural and interaction differences within disordered regions and across protein sets

    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
    UnusedPrivate
    -0.79
    libft
    -0.72
     SqlDbType
    -0.72
    WithIOException
    -0.72
    principalColumn
    -0.72
    ItemBackground
    -0.72
    EndContext
    -0.71
     DRO
    -0.70
    =$?
    -0.70
     textStatus
    -0.68
    POSITIVE LOGITS
     classify
    0.78
     categorize
    0.77
    tify
    0.71
    classify
    0.66
    virons
    0.66
     regroupe
    0.64
     régler
    0.63
     discuss
    0.62
    IFY
    0.62
     glorify
    0.62
    Activations Density 1.393%

    No Known Activations