© 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. 1-CLT-HP
    4. 11726
    Prev
    Next
    INDEX
    Explanations

    er/ed suffixes

    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
    Hons
    -0.42
     verir
    -0.42
    dorfer
    -0.42
    issex
    -0.41
    hæng
    -0.38
    dbg
    -0.38
    wäsche
    -0.37
    Forma
    -0.37
    カー
    -0.37
     Cfr
    -0.37
    POSITIVE LOGITS
    MigrationBuilder
    1.05
    PreferredItem
    0.81
    windowFixed
    0.81
    LookAnd
    0.80
     الرياضيه
    0.77
    DataAnnotations
    0.73
     Biôgrafia
    0.70
    }{*}{
    0.69
    protoimpl
    0.69
     pinulongan
    0.69
    Activations Density 0.073%

    No Known Activations