© 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. 1-CLT-HP
    7. 12021
    Prev
    Next
    INDEX
    Explanations

    groups of people/animals

    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
     himo
    -0.72
     disambiguazione
    -0.69
    IVEREF
    -0.60
    ViewImports
    -0.59
    PreferredItem
    -0.59
    HasForeignKey
    -0.57
    Rüyada
    -0.56
     nakalista
    -0.56
     EconPapers
    -0.54
     of
    -0.54
    POSITIVE LOGITS
     Verſ
    0.60
    UIControlState
    0.59
     velocity
    0.56
    assertRaises
    0.53
    Gön
    0.53
    تور
    0.51
     know
    0.51
    IMENTO
    0.51
    niker
    0.51
    ως
    0.50
    Activations Density 0.015%

    No Known Activations