© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116902
    Prev
    Next
    INDEX
    Explanations

    Mr. Fish Characterization

    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
     military
    -0.07
    military
    -0.06
     воен
    -0.06
     Militar
    -0.06
     Military
    -0.06
    Military
    -0.06
    Border
    -0.06
     başladı
    -0.06
    军事
    -0.06
     топо
    -0.06
    POSITIVE LOGITS
    他に
    0.07
    企业家
    0.07
     selain
    0.07
     workman
    0.06
     предприятий
    0.06
     kinda
    0.06
     empresarios
    0.06
    难度
    0.06
     промышленности
    0.06
     Nigam
    0.06
    Activations Density 0.002%

    No Known Activations