© 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. 5-CLT-HP
    7. 96848
    Prev
    Next
    INDEX
    Explanations

    the, 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
    Aiheesta
    -0.66
    mány
    -0.47
    terase
    -0.43
     estekak
    -0.43
    moveTo
    -0.40
    Witam
    -0.40
    Hochspringen
    -0.40
     днем
    -0.39
    aarrggbb
    -0.38
    Allied
    -0.38
    POSITIVE LOGITS
    BagLayout
    0.84
     nahilalakip
    0.67
    PMailer
    0.59
     ISNI
    0.58
    onedDateTime
    0.57
    WebpackPlugin
    0.57
     jScrollPane
    0.57
    WriteTagHelper
    0.56
    campal
    0.55
    ộn
    0.55
    Activations Density 0.003%

    No Known Activations