© 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. 2640
    Prev
    Next
    INDEX
    Explanations

    references to chemical enzymes, reactions, or processes related to metabolism and enzymatic activity

    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
    曖昧さ回避
    -0.65
    dza
    -0.57
     rač
    -0.55
    vaadin
    -0.53
    AMIENTO
    -0.53
     étanche
    -0.52
    NameInMap
    -0.52
     amplificador
    -0.51
    rootDir
    -0.50
    yfik
    -0.50
    POSITIVE LOGITS
     kinetic
    3.34
     Kinetic
    2.94
    Kinetic
    2.73
    kinetic
    2.61
     kinetics
    2.23
     Kinetics
    1.91
     kine
    1.63
    inetics
    1.21
    inetic
    1.05
    kine
    0.95
    Activations Density 0.003%

    No Known Activations