© 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. 118064
    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
     संवेदना
    -0.07
     麻
    -0.06
     two
    -0.06
    overlapping
    -0.06
     одному
    -0.06
     interceptions
    -0.06
    完全に
    -0.06
     interpretations
    -0.06
     reinterpret
    -0.06
     સેવા
    -0.06
    POSITIVE LOGITS
     плани
    0.07
     votre
    0.06
     klasik
    0.06
    计划
    0.06
     oraz
    0.06
     സമീപ
    0.06
     পরিকল্প
    0.06
     стандарт
    0.06
     orta
    0.06
     प्रातः
    0.06
    Activations Density 0.000%

    No Known Activations