© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130698
    Prev
    Next
    INDEX
    Explanations

    solo career or album

    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
     indicada
    -0.06
     remotely
    -0.06
     conferencing
    -0.06
     customised
    -0.06
     custom
    -0.06
     newest
    -0.06
     quaerat
    -0.06
     Belo
    -0.06
     ತ
    -0.06
     delightfully
    -0.06
    POSITIVE LOGITS
    collisions
    0.07
     mainly
    0.06
     collisions
    0.06
     તેમજ
    0.06
    嗎
    0.06
    了吗
    0.06
    维持
    0.06
     Memphis
    0.06
     proclaiming
    0.06
    吗
    0.06
    Activations Density 0.009%

    No Known Activations