© 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. 15009
    Prev
    Next
    INDEX
    Explanations

    improve

    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
     improve
    -0.65
     migli
    -0.63
    Improve
    -0.62
     improves
    -0.62
     improved
    -0.61
    améli
    -0.61
     förb
    -0.60
     amélior
    -0.59
     migliorare
    -0.59
     Improve
    -0.59
    POSITIVE LOGITS
    PerformLayout
    0.66
     WaitForSeconds
    0.64
    IBOutlet
    0.63
    ChildScrollView
    0.61
    EndInit
    0.60
    VideoCapture
    0.59
    readystatechange
    0.56
    AddTagHelper
    0.55
    antics
    0.54
    horesis
    0.53
    Activations Density 0.017%

    No Known Activations