© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4428
    Prev
    Next
    INDEX
    Explanations

    places

    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
    IntoConstraints
    -0.94
    Tikang
    -0.91
    protoimpl
    -0.90
     تضيفلها
    -0.80
    +:+
    -0.79
    IsMutable
    -0.79
     архивлан
    -0.77
    Diweddarwch
    -0.76
    mybatisplus
    -0.74
    expandindo
    -0.73
    POSITIVE LOGITS
     should
    0.39
    {
    0.38
     screams
    0.37
    brainly
    0.37
     for
    0.34
     trajets
    0.34
    ửi
    0.34
     beyond
    0.34
     {
    0.33
     Vibes
    0.33
    Activations Density 0.002%

    No Known Activations