© 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. 1-CLT-HP
    7. 10433
    Prev
    Next
    INDEX
    Explanations

    weather

    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
     weather
    -1.19
     Weather
    -1.05
    Weather
    -0.95
     WEATHER
    -0.91
    weather
    -0.89
    WEATHER
    -0.88
     climatic
    -0.75
     climate
    -0.72
     meteorological
    -0.72
     Meteorology
    -0.68
    POSITIVE LOGITS
    ंदीखरीदारी
    0.59
     secundarios
    0.53
    man
    0.52
    chain
    0.51
    train
    0.51
    front
    0.50
     cref
    0.49
    go
    0.48
    do
    0.48
    zz
    0.47
    Activations Density 0.007%

    No Known Activations