© 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. 0-CLT-HP
    7. 42518
    Prev
    Next
    INDEX
    Explanations

    Hollywood/movies

    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
    waves
    -0.84
    Waves
    -0.79
     Waves
    -0.73
     waves
    -0.70
    disposable
    -0.64
    wave
    -0.60
     wave
    -0.59
     AssemblyTitle
    -0.59
    Progressive
    -0.58
    MessageTagHelper
    -0.58
    POSITIVE LOGITS
    SharedDtor
    0.87
    ai
    0.67
    Personensuche
    0.66
    ed
    0.66
    ek
    0.65
     nakalista
    0.65
    🎰
    0.61
    ev
    0.60
    bitField
    0.59
    aj
    0.57
    Activations Density 0.122%

    No Known Activations