© 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. 5-CLT-HP
    7. 97009
    Prev
    Next
    INDEX
    Explanations

    picture

    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
    ніципалі
    -0.66
    RegressionTest
    -0.58
     виправивши
    -0.57
    ValueStyle
    -0.57
    出版年
    -0.55
     estimés
    -0.53
     يتيمه
    -0.53
     kaarangay
    -0.53
    inafter
    -0.52
     مشين
    -0.51
    POSITIVE LOGITS
     class
    0.76
    windowFixed
    0.63
     fiction
    0.59
     lesson
    0.58
     lab
    0.58
    class
    0.55
     classes
    0.54
     Class
    0.54
     kelas
    0.53
     teacher
    0.53
    Activations Density 0.001%

    No Known Activations