© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120098
    Prev
    Next
    INDEX
    Explanations

    matrix metalloproteinases

    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
     getting
    -0.06
     retarded
    -0.06
     outfits
    -0.06
    yled
    -0.06
    Getting
    -0.06
    ihad
    -0.05
     развитии
    -0.05
     झाल्यावर
    -0.05
    exhaust
    -0.05
    etet
    -0.05
    POSITIVE LOGITS
    replaced
    0.07
     erset
    0.07
    substr
    0.07
     bloodshed
    0.07
    破坏
    0.07
     użyt
    0.06
     любого
    0.06
     substr
    0.06
    க்கண
    0.06
     ruptura
    0.06
    Activations Density 0.014%

    No Known Activations