© 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. 4-CLT-HP
    7. 756
    Prev
    Next
    INDEX
    Explanations

    viable

    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
    protoimpl
    -0.63
     تضيفلها
    -0.59
    RectangleBorder
    -0.57
    GEBURTSDATUM
    -0.57
     بيها
    -0.57
     متعلقه
    -0.57
    rungsseite
    -0.56
    afficheront
    -0.56
    CPtr
    -0.54
    ⓧ
    -0.54
    POSITIVE LOGITS
     option
    0.78
     long
    0.62
     private
    0.59
     proposition
    0.59
     large
    0.56
     personal
    0.54
    ybė
    0.52
    ாட
    0.51
     public
    0.51
     high
    0.50
    Activations Density 0.004%

    No Known Activations