© 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. 128326
    Prev
    Next
    INDEX
    Explanations

    extremes of minimize/maximize

    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
     probably
    -0.07
     주요
    -0.06
     bazie
    -0.06
     कुल
    -0.06
    od
    -0.06
     most
    -0.06
    すぐ
    -0.06
    主要的
    -0.06
    整体
    -0.06
    主要
    -0.06
    POSITIVE LOGITS
     minimized
    0.08
     minimizing
    0.08
     maximized
    0.07
     minimize
    0.07
     maximizing
    0.07
     maximize
    0.06
     preserving
    0.06
     extreme
    0.06
    也要
    0.06
     minimization
    0.06
    Activations Density 0.008%

    No Known Activations