© 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. 1053
    Prev
    Next
    INDEX
    Explanations

    Any

    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
    }{*}{
    -0.57
     aceptas
    -0.54
    ynchronous
    -0.50
     Another
    -0.50
    they
    -0.49
     noqa
    -0.48
     kic
    -0.47
    protoimpl
    -0.47
    UMBUS
    -0.45
     estabiliz
    -0.45
    POSITIVE LOGITS
    eleste
    0.70
     CreateTagHelper
    0.67
     الدولى
    0.60
    CodedInputStream
    0.60
    yntaxException
    0.60
    AddTagHelper
    0.58
    sizeCache
    0.56
     typelib
    0.56
     StringTokenizer
    0.56
    发表于
    0.55
    Activations Density 0.001%

    No Known Activations