© 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. 96714
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
     terakhir
    -0.40
     jene
    -0.39
    No
    -0.39
    MessageTagHelper
    -0.38
    पया
    -0.37
    unfinished
    -0.34
     últimas
    -0.34
    tığı
    -0.33
     aqueles
    -0.33
    ><!--
    -0.33
    POSITIVE LOGITS
    KEYCODE
    0.87
    SequentialGroup
    0.75
     незавершена
    0.75
     ProtoMessage
    0.72
     a
    0.68
    contentLoaded
    0.68
    LookAnd
    0.67
    ffilm
    0.66
     مواليد
    0.65
    Soorten
    0.65
    Activations Density 0.011%

    No Known Activations