© 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-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4973
    Prev
    Next
    INDEX
    Explanations

    references to the name "Ko," particularly variations and stylizations thereof

    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
     CPF
    -0.60
     Rao
    -0.59
    Rao
    -0.59
    AndEndTag
    -0.58
     Crowley
    -0.56
     Krä
    -0.56
    RenderAtEndOf
    -0.55
     tung
    -0.54
    adog
    -0.54
    principalTable
    -0.53
    POSITIVE LOGITS
    ko
    3.23
    Ko
    2.86
    KO
    2.78
     Ko
    2.73
     ko
    2.69
     KO
    2.30
    koj
    1.48
    Koz
    1.41
    Koala
    1.40
    koa
    1.38
    Activations Density 0.026%

    No Known Activations