© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120710
    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
    使用了
    -0.07
    apparition
    -0.07
    datei
    -0.07
    下载
    -0.07
    下載
    -0.06
     회사
    -0.06
     apparition
    -0.06
     узна
    -0.06
    rought
    -0.06
    DVD
    -0.06
    POSITIVE LOGITS
    izzare
    0.06
    ,
    0.06
    detector
    0.06
     remind
    0.05
     similarities
    0.05
     forestry
    0.05
     ஒற்று
    0.05
     Struct
    0.05
     कदा
    0.05
    odd
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.