© 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. 1-CLT-HP
    7. 15619
    Prev
    Next
    INDEX
    Explanations

    scientific and historical contexts

    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
    abestanden
    -0.81
     مشين
    -0.77
     CreateTagHelper
    -0.77
     Pliocene
    -0.74
     Ordovician
    -0.73
    
    -0.69
     CYTHON
    -0.69
     Eocene
    -0.67
     $_"
    -0.67
    aarrggbb
    -0.67
    POSITIVE LOGITS
     port
    0.48
    te
    0.47
     hel
    0.46
    -
    0.46
    protoimpl
    0.46
     th
    0.45
     d
    0.45
    ?
    0.44
     inner
    0.44
     HAR
    0.44
    Activations Density 0.071%

    No Known Activations