© 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. 14657
    Prev
    Next
    INDEX
    Explanations

    storms and 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
    ="@+
    -0.50
     onOptions
    -0.50
     om
    -0.50
    GEBURTSDATUM
    -0.48
     ap
    -0.47
     vid
    -0.47
     ô
    -0.47
     che
    -0.47
     gal
    -0.46
    opted
    -0.46
    POSITIVE LOGITS
     itſelf
    0.78
     ―――――
    0.77
     myſelf
    0.74
     Jefus
    0.72
     photolibrary
    0.71
     moschino
    0.71
     Efq
    0.69
     Monfieur
    0.66
     hydrodynamic
    0.64
     femininas
    0.63
    Activations Density 0.009%

    No Known Activations