© 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. 6564
    Prev
    Next
    INDEX
    Explanations

    references to specific forms of the word "og," likely referring to "O" genes or related molecules

    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
    fromCharCode
    -0.61
    DBNull
    -0.57
     mxArray
    -0.56
    encodeWith
    -0.54
    getCause
    -0.54
    Identity
    -0.51
    WriteTagHelper
    -0.50
    namt
    -0.49
    bital
    -0.49
     Ton
    -0.49
    POSITIVE LOGITS
    og
    3.91
    OG
    3.00
    ogs
    2.39
    oga
    1.79
    Og
    1.74
     OG
    1.68
    OGA
    1.63
    ogi
    1.61
    ogar
    1.58
    ogg
    1.55
    Activations Density 0.009%

    No Known Activations