© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 323
    Prev
    Next
    INDEX
    Explanations

    ea

    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
    saraba
    -0.65
    出版年
    -0.65
    setopt
    -0.65
    detectChanges
    -0.58
    webElement
    -0.57
    GEBURTSDATUM
    -0.56
    OGND
    -0.56
    omock
    -0.56
     ComVisible
    -0.55
    Vidite
    -0.54
    POSITIVE LOGITS
    ността
    0.45
     nennen
    0.44
    IMPORTED
    0.43
    stoff
    0.42
     mero
    0.41
    anyi
    0.41
    ModelSerializer
    0.40
    Handlung
    0.40
    Glej
    0.40
     CreateTagHelper
    0.39
    Activations Density 0.003%

    No Known Activations