© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13727
    Prev
    Next
    INDEX
    Explanations

    references to judicial juries or jurors

    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
    aur
    -0.72
    Hozzáférés
    -0.56
    ํา
    -0.50
     resourceCulture
    -0.50
     QName
    -0.49
    érale
    -0.49
    astify
    -0.48
    isNullOrEmpty
    -0.48
    FXMLLoader
    -0.47
    Карьера
    -0.47
    POSITIVE LOGITS
     Jur
    1.28
     dumpster
    0.94
    Jur
    0.86
    /***/
    0.79
     stray
    0.79
    脚注の使い方
    0.75
     PSR
    0.73
     Nobel
    0.72
     Mandela
    0.71
     PMA
    0.69
    Activations Density 0.010%

    No Known Activations