© 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. 93686
    Prev
    Next
    INDEX
    Explanations

    fly

    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
     fly
    -2.67
     flying
    -2.64
     flight
    -2.47
     flew
    -2.38
     flown
    -2.28
    flying
    -2.27
     Fly
    -2.17
     Flight
    -2.16
    Flying
    -2.16
     Flying
    -2.14
    POSITIVE LOGITS
    PasswordEncoder
    0.57
    path
    0.56
    lines
    0.47
     esper
    0.46
    PageContext
    0.46
    s
    0.46
     in
    0.45
    box
    0.45
    tte
    0.44
    sticks
    0.44
    Activations Density 1.776%

    No Known Activations