Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39558
    Prev
    Next
    INDEX
    Explanations

    pay

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pay
    -1.62
    pay
    -1.50
     Pay
    -1.46
    Pay
    -1.39
     PAY
    -1.17
    PAY
    -1.08
     spend
    -1.06
     payment
    -1.04
     Payment
    -1.02
     pago
    -1.02
    POSITIVE LOGITS
    OrBuilder
    0.57
    pośred
    0.57
     giapp
    0.52
    wise
    0.52
     énergé
    0.52
     picioare
    0.51
     Shakspeare
    0.51
    seamnă
    0.51
     noastre
    0.49
    alike
    0.49
    Activations Density 0.998%

    No Known Activations