© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 771
    Prev
    Next
    INDEX
    Explanations

    words related to chemical reactions and scientific processes

    oai_token-act-pair · gemini-2.0-flash
    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
    wpi
    -0.54
    fund
    -0.52
    Sos
    -0.52
    cycline
    -0.52
     Finder
    -0.52
    TestingModule
    -0.52
    Fund
    -0.51
     supp
    -0.50
     Ringo
    -0.50
     offering
    -0.49
    POSITIVE LOGITS
     oxidation
    1.10
     Oxidation
    1.09
     hydrolysis
    0.82
    oxidation
    0.82
     digestion
    0.79
     metabolism
    0.77
     oxidative
    0.75
    tabolism
    0.75
     Digestion
    0.75
     photosynthesis
    0.74
    Activations Density 1.687%

    No Known Activations