© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92642
    Prev
    Next
    INDEX
    Explanations

    imide param

    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
     Germania
    -1.34
    imide
    -1.09
    Germania
    -0.86
     tartalomajánló
    -0.53
    Hauptartikel
    -0.50
    Persön
    -0.46
    stander
    -0.45
    kosh
    -0.44
    utriche
    -0.44
    ganu
    -0.44
    POSITIVE LOGITS
    Geplaatst
    0.73
    sidemargin
    0.62
    TagHelper
    0.58
    matchCondition
    0.58
    IsContent
    0.57
     BUN
    0.56
    argli
    0.55
    BASEPATH
    0.54
    SuppressMessage
    0.54
     Infórmanos
    0.54
    Activations Density 0.554%

    No Known Activations