© 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. 3057
    Prev
    Next
    INDEX
    Explanations

    references to customer or client information

    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
     readers
    -0.87
    esgue
    -0.84
     listeners
    -0.84
    Readers
    -0.83
     viewers
    -0.81
     Readers
    -0.81
    MLLoader
    -0.79
     fans
    -0.77
     Fans
    -0.73
     audiences
    -0.71
    POSITIVE LOGITS
     customer
    2.77
     Customer
    2.50
    Customer
    2.39
    customer
    2.38
     customers
    2.27
     CUSTOMER
    2.20
    CUSTOMER
    2.13
     Customers
    2.08
    customers
    2.03
     getCustomer
    2.02
    Activations Density 0.012%

    No Known Activations