© 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-CLT-HP
    7. 93504
    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
    -2.86
     Car
    -2.25
    car
    -1.90
    Car
    -1.78
     CAR
    -1.52
     cars
    -1.41
    CAR
    -1.13
     Cars
    -1.02
    カー
    -0.98
    ecar
    -0.93
    POSITIVE LOGITS
     myſelf
    1.80
     Efq
    1.80
     itſelf
    1.77
     Monfieur
    1.76
     Jefus
    1.62
     whoſe
    1.55
     Theſe
    1.55
    ſelf
    1.52
     Anſ
    1.52
     purpoſe
    1.52
    Activations Density 0.055%

    No Known Activations