© 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. 0-RES-MATRYOSHKA-DC
    7. 15141
    Prev
    Next
    INDEX
    Explanations

    references to a specific personal 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
     Jo
    -1.32
     JO
    -1.00
     jo
    -0.97
    Jo
    -0.93
    PerformLayout
    -0.81
     Joi
    -0.75
     Joaquin
    -0.68
     JoJo
    -0.65
     Joel
    -0.63
    ijo
    -0.62
    POSITIVE LOGITS
    jo
    1.91
    joit
    0.70
    disposing
    0.68
     चीज़ों
    0.64
    licability
    0.57
    ubility
    0.56
    endrait
    0.56
     GreatSchools
    0.55
     createState
    0.54
     écoulé
    0.52
    Activations Density 0.001%

    No Known Activations