© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41512
    Prev
    Next
    INDEX
    Explanations

    Increased

    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
    tia
    -0.68
    ing
    -0.65
    ative
    -0.56
    times
    -0.51
    thia
    -0.50
    a
    -0.49
    Chham
    -0.48
    :✨
    -0.47
    ging
    -0.47
    bean
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.83
     تضيفلها
    0.83
     виправивши
    0.77
     blessés
    0.77
    umumkan
    0.73
     Vikipedi
    0.72
     whofe
    0.67
    MessageTagHelper
    0.66
     سكانية
    0.65
     undangan
    0.65
    Activations Density 0.358%

    No Known Activations