© 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. 118060
    Prev
    Next
    INDEX
    Explanations

    diphenylanthphotovoltaici-ebi-deriv

    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
     estim
    -0.07
     razem
    -0.07
     помощь
    -0.06
    )..
    -0.06
     miscellaneous
    -0.06
    )$,
    -0.06
     기본적인
    -0.06
     ambulance
    -0.06
    ..(
    -0.06
     उपचार
    -0.06
    POSITIVE LOGITS
     microstructure
    0.06
     consequent
    0.06
     achieve
    0.06
     photovolta
    0.06
    repeated
    0.06
    解消
    0.06
    တိုင်း
    0.06
     증가
    0.06
     radically
    0.06
     Presently
    0.06
    Activations Density 0.014%

    No Known Activations