© 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. 129868
    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
     methodologies
    -0.06
     detalles
    -0.06
     অন্তর্গত
    -0.06
    中所
    -0.06
     paced
    -0.06
    ToSort
    -0.06
     incorrectly
    -0.06
     베타
    -0.05
     forgot
    -0.05
    人们
    -0.05
    POSITIVE LOGITS
    Obviously
    0.06
    puter
    0.06
    obviously
    0.06
    put
    0.06
    While
    0.06
     harvester
    0.05
     கிட்டத்தட்ட
    0.05
     отде
    0.05
     by
    0.05
     évidemment
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.