© 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. 194
    Prev
    Next
    INDEX
    Explanations

    a

    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
    LookAnd
    -0.68
    UnusedPrivate
    -0.65
     économ
    -0.65
     éte
    -0.65
    utilisons
    -0.64
     оригіналу
    -0.63
     conférences
    -0.61
     NSCoder
    -0.61
     pulumi
    -0.60
     muerta
    -0.60
    POSITIVE LOGITS
     daily
    0.66
     autorytatywna
    0.52
    المناصب
    0.51
     continuing
    0.48
     per
    0.48
    awaiter
    0.47
     wound
    0.47
     continued
    0.47
    indrops
    0.46
     viewDidLoad
    0.45
    Activations Density 0.006%

    No Known Activations