© 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. 5-CLT-HP
    7. 98264
    Prev
    Next
    INDEX
    Explanations

    ownership, creation

    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
     âmes
    -0.82
     preuves
    -0.82
     vérit
    -0.82
     vectorielles
    -0.81
     propOrder
    -0.81
     bénéfices
    -0.81
     genoux
    -0.80
     enfans
    -0.80
     femininos
    -0.80
     varandra
    -0.80
    POSITIVE LOGITS
     games
    0.59
     pizzas
    0.52
     pens
    0.49
     ads
    0.49
     brochures
    0.49
     versions
    0.49
     commercials
    0.48
     books
    0.48
     tacos
    0.48
     movies
    0.47
    Activations Density 0.001%

    No Known Activations