© 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. 10491
    Prev
    Next
    INDEX
    Explanations

    film production

    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
    homonymie
    -0.54
     filmy
    -0.52
     film
    -0.50
    ्रीय
    -0.49
    Revenir
    -0.49
    новништво
    -0.48
    hålla
    -0.48
    もちゃ
    -0.47
     hjer
    -0.46
    ViewImports
    -0.46
    POSITIVE LOGITS
    LookAnd
    0.68
     transfieras
    0.64
    WithIOException
    0.63
    featureID
    0.61
     AssemblyProduct
    0.56
     TextAppearance
    0.56
    UrlResolution
    0.54
    setPointSize
    0.54
    PostExecute
    0.54
    octanol
    0.53
    Activations Density 0.078%

    No Known Activations