© 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. 118617
    Prev
    Next
    INDEX
    Explanations

    CD4/CD8 ratio

    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
     pairwise
    -0.06
     mAb
    -0.06
     abbastanza
    -0.06
     sketchy
    -0.06
     separatist
    -0.06
     पेशे
    -0.06
     merciless
    -0.06
     longitudine
    -0.06
     harshly
    -0.06
     spooky
    -0.06
    POSITIVE LOGITS
    Chef
    0.06
     Chef
    0.06
     beberapa
    0.06
     अपराध
    0.06
     expand
    0.06
     chefs
    0.06
    能够在
    0.06
     result
    0.06
    一些
    0.06
     ব্যাপার
    0.05
    Activations Density 0.003%

    No Known Activations