© 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. 129828
    Prev
    Next
    INDEX
    Explanations

    matrix or nanotubes

    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
     ৫
    -0.07
     удалось
    -0.06
     कट्टर
    -0.06
     токси
    -0.06
     تلك
    -0.06
     ৬
    -0.06
     microbiome
    -0.06
    bedkar
    -0.06
     typography
    -0.06
     관광
    -0.06
    POSITIVE LOGITS
     intermittent
    0.06
     lâu
    0.06
     petition
    0.06
    慟
    0.06
    WHEN
    0.06
     प्रतिस्पर्
    0.06
    他に
    0.06
    Ax
    0.05
     substitution
    0.05
     diario
    0.05
    Activations Density 0.003%

    No Known Activations