© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119040
    Prev
    Next
    INDEX
    Explanations

    methotrexate and immunosuppressive agents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     service
    -0.06
     Scotch
    -0.06
    毫不
    -0.06
    专项
    -0.06
    㳚
    -0.06
     استفاده
    -0.06
     desl
    -0.06
    Lux
    -0.06
     applic
    -0.06
     서비스
    -0.05
    POSITIVE LOGITS
     mittlerweile
    0.07
    いま
    0.07
     limitaciones
    0.07
     سلامت
    0.06
    capacity
    0.06
     Collected
    0.06
     cette
    0.06
    この
    0.06
     ছাড়
    0.06
     약
    0.06
    Activations Density 0.008%

    No Known Activations