© 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. 5-CLT-HP
    7. 3345
    Prev
    Next
    INDEX
    Explanations

    entertainment

    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
     genoux
    -0.68
    ViewImports
    -0.68
     épaules
    -0.60
     giapp
    -0.60
    raszam
    -0.57
     cérami
    -0.57
    AllAfrica
    -0.56
    Kjelder
    -0.55
     engraçadas
    -0.55
     parteci
    -0.55
    POSITIVE LOGITS
    PerformLayout
    0.54
    DispatchToProps
    0.49
     emergent
    0.48
    PyExc
    0.48
    findpost
    0.48
     activities
    0.47
     original
    0.47
     Chwiliwch
    0.47
    起来
    0.45
     별
    0.45
    Activations Density 0.000%

    No Known Activations