© 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. 0-CLT-HP
    7. 94005
    Prev
    Next
    INDEX
    Explanations

    Zee

    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
     W
    -0.68
     der
    -0.59
     Real
    -0.58
     K
    -0.57
     
    -0.52
    el
    -0.51
     UIKit
    -0.51
     (
    -0.50
    real
    -0.50
     the
    -0.49
    POSITIVE LOGITS
     myſelf
    1.39
     itſelf
    1.34
     Reſ
    1.33
     Houſe
    1.31
     Efq
    1.29
     themſelves
    1.28
     pleaſure
    1.27
     himſelf
    1.27
     ſche
    1.24
     Monfieur
    1.23
    Activations Density 1.462%

    No Known Activations