© 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. 119088
    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
     vag
    -0.05
     Education
    -0.05
     primera
    -0.05
    ilih
    -0.05
    test
    -0.05
    èr
    -0.05
     negoci
    -0.05
    US
    -0.05
     selected
    -0.05
     custom
    -0.05
    POSITIVE LOGITS
     предотвра
    0.08
    有效地
    0.06
    Bibliography
    0.06
     proactively
    0.06
    डली
    0.06
     menghindari
    0.06
    guard
    0.06
    Drain
    0.06
    Regardless
    0.06
     Bibliography
    0.06
    Activations Density 0.003%

    No Known Activations