© 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. 15430
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    tvguidetime
    -0.87
    ReusableCell
    -0.79
     CreateTagHelper
    -0.74
    पया
    -0.73
     تضيفلها
    -0.71
    enderror
    -0.70
    PMailer
    -0.69
    بوابة
    -0.68
    าสตร์
    -0.67
     MessageBoxIcon
    -0.66
    POSITIVE LOGITS
    collapsible
    0.43
     indictment
    0.40
     Monticello
    0.39
    әр
    0.38
     Ollie
    0.38
     Burnley
    0.38
     Samp
    0.38
    springframework
    0.38
     BLOOM
    0.37
    addColumn
    0.37
    Activations Density 0.400%

    No Known Activations