© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118799
    Prev
    Next
    INDEX
    Explanations

    automobile and related industries

    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
    infection
    -0.07
     infection
    -0.07
    irling
    -0.07
     Infection
    -0.07
     canonically
    -0.07
    Psych
    -0.06
    大学生
    -0.06
     zapewn
    -0.06
     instructional
    -0.06
    防护
    -0.06
    POSITIVE LOGITS
     lobbyists
    0.07
     automotive
    0.07
    汽车
    0.07
     mergers
    0.06
     cars
    0.06
     mutual
    0.06
     автомоби
    0.06
    互
    0.06
     global
    0.06
     automobile
    0.06
    Activations Density 0.001%

    No Known Activations