© 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. 117758
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     abhängig
    -0.06
     соответствии
    -0.06
    ǜ
    -0.06
    喜欢
    -0.06
     dựa
    -0.06
     เรา
    -0.06
     bijvoorbeeld
    -0.06
    urken
    -0.06
     também
    -0.06
    ibouti
    -0.06
    POSITIVE LOGITS
     excellent
    0.06
     additional
    0.06
     জ্বল
    0.06
     Appart
    0.06
    !
    0.06
     ludicrous
    0.06
     ostatnich
    0.06
    fatter
    0.05
     نوشته
    0.05
     remarkable
    0.05
    Activations Density 0.000%

    No Known Activations