© 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. 119007
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     rapporti
    -0.07
     claim
    -0.06
     Disposition
    -0.06
    Claim
    -0.06
     permanente
    -0.06
     permanent
    -0.06
     claims
    -0.06
     claimed
    -0.06
     Permanent
    -0.06
     promise
    -0.06
    POSITIVE LOGITS
    Searching
    0.08
     Searching
    0.07
    buscar
    0.07
    を集
    0.07
    Trying
    0.07
    を探
    0.06
     questão
    0.06
     searching
    0.06
     venturing
    0.06
    搜索
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.