© 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. 121024
    Prev
    Next
    INDEX
    Explanations

    Knuth-Morris-Pratt algorithm

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    >
    -0.06
     Maverick
    -0.06
     ಕ್ರ
    -0.06
     مخطط
    -0.06
     Lottery
    -0.06
     自己
    -0.06
    brackets
    -0.06
     Ги
    -0.05
     terakhir
    -0.05
    த்தையும்
    -0.05
    POSITIVE LOGITS
     größ
    0.07
    imshow
    0.07
     novos
    0.06
     nowoczes
    0.06
     novo
    0.06
     جدید
    0.06
     nuove
    0.06
     новом
    0.06
     तुम्हारे
    0.06
     nouveau
    0.06
    Activations Density 0.002%

    No Known Activations