© 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. 4128
    Prev
    Next
    INDEX
    Explanations

    republish/republic

    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
    IsMutable
    -0.83
    ETER
    -0.56
     CreateTagHelper
    -0.53
     OFDb
    -0.53
    SError
    -0.52
     Card
    -0.51
     INTEL
    -0.50
    الإنجليزية
    -0.49
    Pronunciation
    -0.49
     Balance
    -0.49
    POSITIVE LOGITS
    lish
    0.71
     Мексичка
    0.55
     useContext
    0.47
     ویکی‌پدیا
    0.47
     plc
    0.47
     jspb
    0.47
    LayoutConstraint
    0.46
    urst
    0.46
    rint
    0.46
     jsPsych
    0.45
    Activations Density 0.001%

    No Known Activations