© 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. 118339
    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
     каждым
    -0.07
     Dieu
    -0.06
    Brain
    -0.06
     واضح
    -0.06
     EACH
    -0.06
    Each
    -0.05
     polisi
    -0.05
     explan
    -0.05
     standout
    -0.05
    Теперь
    -0.05
    POSITIVE LOGITS
     suspension
    0.06
     suspensions
    0.06
    amaks
    0.06
    maybe
    0.06
    σον
    0.06
    其他的
    0.06
     myös
    0.06
     habe
    0.05
     største
    0.05
    最後まで
    0.05
    Activations Density 0.000%

    No Known Activations