© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130682
    Prev
    Next
    INDEX
    Explanations

    hypotension, hemodialysis, OH

    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
    どんどん
    -0.06
    matik
    -0.06
     ক্রমাগত
    -0.06
     otomatis
    -0.06
    ણો
    -0.06
     टा
    -0.06
     programma
    -0.06
     tega
    -0.06
    質な
    -0.06
     excellent
    -0.06
    POSITIVE LOGITS
     它
    0.07
     encounters
    0.06
    碰
    0.06
    保管
    0.06
    一些
    0.06
     verantwortlich
    0.06
    相似
    0.06
     *-
    0.06
     behaves
    0.06
    扰
    0.06
    Activations Density 0.039%

    No Known Activations