© 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. 130908
    Prev
    Next
    INDEX
    Explanations

    innovative ideas

    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
    Not in Any Lists

    No Comments

    Negative Logits
     পরীক্ষা
    -0.07
    Gin
    -0.06
    FormControl
    -0.06
    ತಿ
    -0.06
     bagian
    -0.06
     rebuild
    -0.06
    Hint
    -0.06
     обстоя
    -0.06
     isTestSource
    -0.06
     fights
    -0.06
    POSITIVE LOGITS
     иннова
    0.07
     innovative
    0.07
     национальной
    0.07
     innovación
    0.06
     innov
    0.06
     innovation
    0.06
     Innovative
    0.06
     creativity
    0.06
     innovator
    0.06
     jego
    0.06
    Activations Density 0.004%

    No Known Activations