© 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. 115923
    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
    Negative Logits
     계산
    -0.07
     yksi
    -0.07
    发送
    -0.07
     endangering
    -0.07
     calculi
    -0.07
     quase
    -0.07
     unsurpassed
    -0.07
    mitting
    -0.07
     undeniably
    -0.07
     seldom
    -0.07
    POSITIVE LOGITS
     image
    0.06
     ancak
    0.05
    client
    0.05
    /
    0.05
     avions
    0.05
     Media
    0.05
    即可
    0.05
     keyboard
    0.05
    image
    0.05
    Real
    0.05
    Activations Density 0.004%

    No Known Activations