© 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. 118777
    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
     offers
    -0.07
     preconditions
    -0.07
     like
    -0.06
     LIKE
    -0.06
     vous
    -0.06
     seperti
    -0.06
     مثل
    -0.06
    特性
    -0.06
    Instead
    -0.06
    踩
    -0.06
    POSITIVE LOGITS
    9
    0.06
    8
    0.06
     assistenza
    0.06
    7
    0.06
     என்ன
    0.06
    ulho
    0.06
    墂
    0.06
    buro
    0.05
     което
    0.05
     dedicated
    0.05
    Activations Density 0.002%

    No Known Activations