© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13376
    Prev
    Next
    INDEX
    Explanations

    references to specific chemical substances, particularly "glut" and "gluten."

    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
    loroethane
    -0.63
    RegressionTest
    -0.60
     révélé
    -0.58
    beginTransaction
    -0.57
    Aww
    -0.56
     propOrder
    -0.55
    "?>
    -0.54
     Vergara
    -0.53
    sikal
    -0.53
    เท้า
    -0.52
    POSITIVE LOGITS
    glut
    3.84
    GLUT
    2.47
     GLUT
    2.27
     Glut
    1.91
     glut
    1.90
     gluten
    0.93
    gluten
    0.88
    Gluten
    0.84
     Gluten
    0.76
     glutathione
    0.71
    Activations Density 0.004%

    No Known Activations