© 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. 130367
    Prev
    Next
    INDEX
    Explanations

    tile, wrap, repeat, bounds

    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
     movable
    -0.08
     mycursor
    -0.07
     moveable
    -0.07
     atualizar
    -0.07
     modernist
    -0.07
     desmont
    -0.06
    晞
    -0.06
    👱
    -0.06
     Bly
    -0.06
     আবারও
    -0.06
    POSITIVE LOGITS
    മായിരുന്നു
    0.06
    补
    0.06
    department
    0.06
     department
    0.06
     National
    0.05
     fait
    0.05
     bij
    0.05
    繩
    0.05
     худож
    0.05
     departments
    0.05
    Activations Density 0.001%

    No Known Activations