© 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-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7223
    Prev
    Next
    INDEX
    Explanations

    references to chemical compounds involving oxide materials

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edi
    -0.57
     للمعارف
    -0.56
     conditions
    -0.52
     Mitter
    -0.51
    CHW
    -0.48
     Mehdi
    -0.48
     lượt
    -0.47
    ь
    -0.47
    sib
    -0.47
     Freddie
    -0.47
    POSITIVE LOGITS
     oxide
    3.55
     Oxide
    3.23
     oxides
    2.77
    oxide
    2.52
    xide
    1.44
     dioxide
    1.09
     monoxide
    1.05
     Dioxide
    1.03
     OX
    1.00
    氧化
    1.00
    Activations Density 0.011%

    No Known Activations