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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97501
    Prev
    Next
    INDEX
    Explanations

    car

    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
     car
    -2.13
     Car
    -1.50
    Car
    -1.07
    car
    -0.92
     CAR
    -0.77
     def
    -0.69
     auto
    -0.66
     cars
    -0.66
     par
    -0.65
     de
    -0.64
    POSITIVE LOGITS
     itſelf
    1.17
     Monfieur
    1.17
     myſelf
    1.10
     ſche
    1.05
     purpoſe
    0.98
     chré
    0.97
     colorés
    0.97
     noires
    0.97
     florales
    0.96
     sauvages
    0.96
    Activations Density 0.023%

    No Known Activations