© 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. 15219
    Prev
    Next
    INDEX
    Explanations

    Lucie

    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
    Hochspringen
    -0.72
    AsUp
    -0.70
     ***!
    -0.69
     utafitiHapana
    -0.62
    expandindo
    -0.61
     centrifuge
    -0.58
     AssemblyTitle
    -0.57
     centrifug
    -0.57
    IUrlHelper
    -0.56
    GOTREF
    -0.55
    POSITIVE LOGITS
    GenerationType
    0.63
    danno
    0.54
     Mothers
    0.51
    deluxe
    0.51
     Desmond
    0.50
    pozycji
    0.50
     pinulongan
    0.50
    owol
    0.49
    المكان
    0.49
    parfum
    0.48
    Activations Density 0.036%

    No Known Activations