© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 6822
    Prev
    Next
    INDEX
    Explanations

    references to chemical radicals involved in antioxidant activity and oxidative stress

    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
     Carri
    -0.70
    bootstrapcdn
    -0.69
     Yom
    -0.69
     незавершена
    -0.68
    TEMPLATES
    -0.68
     Timor
    -0.68
     TestBed
    -0.67
     مرئيه
    -0.67
    consulté
    -0.66
     Aven
    -0.64
    POSITIVE LOGITS
     radical
    2.66
    radical
    2.59
     Radical
    2.56
    Radical
    2.48
     Rad
    2.47
    Rad
    2.45
     radicals
    2.42
     radikal
    2.06
     rad
    2.00
    rad
    1.93
    Activations Density 0.019%

    No Known Activations