© 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. 97341
    Prev
    Next
    INDEX
    Explanations

    {

    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
    DoubleQuotes
    -0.57
     للاسماء
    -0.52
    enterOuterAlt
    -0.51
    Билгалдахарш
    -0.51
     membagikan
    -0.51
     arrivée
    -0.49
     SafeMath
    -0.49
    AutoScale
    -0.48
    Personendaten
    -0.47
     nascimento
    -0.47
    POSITIVE LOGITS
    Derbyniad
    0.60
    sidemargin
    0.59
    DockStyle
    0.58
    зулта
    0.56
    TagHelper
    0.56
    Kontrola
    0.56
     Chwiliwch
    0.56
     Millennium
    0.55
     mxArray
    0.55
    WithIOException
    0.55
    Activations Density 0.333%

    No Known Activations