© 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. 131065
    Prev
    Next
    INDEX
    Explanations

    HIV-related diseases and infections

    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
     angenommen
    -0.06
     кто
    -0.06
     wedding
    -0.06
     Negeri
    -0.06
     unnamed
    -0.06
     people
    -0.06
     brides
    -0.06
     legitimacy
    -0.06
     credible
    -0.06
     vows
    -0.06
    POSITIVE LOGITS
     этот
    0.07
     starved
    0.06
    skeleton
    0.06
     malnourished
    0.06
    饿
    0.06
    餓
    0.06
     শাক
    0.06
     depleted
    0.06
     Produkten
    0.06
     цей
    0.05
    Activations Density 0.010%

    No Known Activations