© 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. 130562
    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
     Система
    -0.06
    ometr
    -0.06
     bullshit
    -0.06
     неизвест
    -0.06
     Illusion
    -0.05
     версии
    -0.05
     сосре
    -0.05
     Referential
    -0.05
     sekund
    -0.05
     остаются
    -0.05
    POSITIVE LOGITS
     finally
    0.07
     róż
    0.07
     आखिरकार
    0.07
    finally
    0.06
     for
    0.06
     commencer
    0.06
     eased
    0.06
     finalmente
    0.06
    终于
    0.06
     accommodates
    0.06
    Activations Density 0.000%

    No Known Activations