© 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. 3133
    Prev
    Next
    INDEX
    Explanations

    references to a particular character named Ky, specifically identifying mentions or mentions of her name

    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
     חיצוניים
    -0.78
     onBind
    -0.54
    PathParam
    -0.52
     ModelExpression
    -0.51
    انيف
    -0.51
    Diwedd
    -0.51
     CreateTagHelper
    -0.50
    Zeneca
    -0.50
    chodzą
    -0.50
    djangoproject
    -0.49
    POSITIVE LOGITS
    ky
    3.73
    KY
    2.78
     ky
    2.31
    Ky
    2.25
     Ky
    2.14
    kyt
    1.89
     KY
    1.87
    kyo
    1.35
    kyl
    1.33
    kyu
    1.27
    Activations Density 0.028%

    No Known Activations