© 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. 4-CLT-HP
    7. 303
    Prev
    Next
    INDEX
    Explanations

    Quizzes or printers

    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
    ^(@)
    -0.57
    ship
    -0.57
    rrggbb
    -0.56
     forState
    -0.55
     Signalez
    -0.54
     foul
    -0.54
     leſs
    -0.50
     uſed
    -0.49
    PreferredItem
    -0.48
    новниш
    -0.48
    POSITIVE LOGITS
    esModule
    0.52
     CreateTagHelper
    0.50
    ParallelGroup
    0.48
    á
    0.48
    veni
    0.47
    twimg
    0.45
     mendatang
    0.45
     CRIST
    0.45
    à
    0.44
    annica
    0.44
    Activations Density 0.000%

    No Known Activations