© 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. 4067
    Prev
    Next
    INDEX
    Explanations

    references to chemical oxidation processes

    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
    ennon
    -0.60
    forChild
    -0.55
     ViewGroup
    -0.51
     phon
    -0.48
    eden
    -0.47
     inst
    -0.46
     braço
    -0.46
    Nicky
    -0.46
     tayo
    -0.45
    琼
    -0.45
    POSITIVE LOGITS
     oxidation
    2.95
     oxid
    2.75
     Oxidation
    2.64
     Oxid
    2.61
     oxidized
    2.42
    oxid
    2.41
     oxidative
    2.38
    oxidation
    2.38
     oxidizing
    2.31
    Oxid
    2.22
    Activations Density 0.013%

    No Known Activations