© 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. 120814
    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
     conceived
    -0.06
     simply
    -0.06
     ,"
    -0.06
    ...."
    -0.06
     inquired
    -0.06
     Defensive
    -0.06
     IEP
    -0.06
     guer
    -0.05
     VLAN
    -0.05
     proximity
    -0.05
    POSITIVE LOGITS
     diversi
    0.07
     seperti
    0.06
     mehrere
    0.06
     plusieurs
    0.06
     Hundreds
    0.06
    了几
    0.06
     thousands
    0.06
    Hundreds
    0.06
     ২০১৪
    0.06
     flera
    0.06
    Activations Density 0.000%

    No Known Activations