© 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. 130858
    Prev
    Next
    INDEX
    Explanations

    in vivo vs in vitro experiments

    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
     transm
    -0.06
     başlayan
    -0.06
     például
    -0.06
     första
    -0.06
     depois
    -0.05
     efter
    -0.05
     neglected
    -0.05
    вар
    -0.05
    ภายใน
    -0.05
     Holman
    -0.05
    POSITIVE LOGITS
     current
    0.07
     have
    0.07
     attuale
    0.07
    单独
    0.07
    attuale
    0.07
     artificially
    0.06
     one
    0.06
    current
    0.06
     hypoallergenic
    0.06
     현재
    0.06
    Activations Density 0.049%

    No Known Activations