© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130904
    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
    使得
    -0.06
     metall
    -0.06
     plentiful
    -0.06
    典型
    -0.06
    *-
    -0.06
     reputable
    -0.06
     hacen
    -0.06
    だけでなく
    -0.06
    even
    -0.05
     tendremos
    -0.05
    POSITIVE LOGITS
     there
    0.08
    There
    0.07
     иначе
    0.06
     सर्कल
    0.06
     יותר
    0.06
     благодаря
    0.06
    those
    0.06
    来自于
    0.06
     There
    0.06
    progressbar
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.