© 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. 3654
    Prev
    Next
    INDEX
    Explanations

    do

    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
     '\\;'
    -0.68
    __':
    -0.67
    dibles
    -0.66
    numerusform
    -0.63
    WriteTagHelper
    -0.63
    GEBURTSDATUM
    -0.63
     '*')
    -0.62
    CppCodeGen
    -0.60
     Bourgoin
    -0.60
    DoubleQuotes
    -0.60
    POSITIVE LOGITS
     aceptas
    0.55
     so
    0.51
     erstes
    0.47
     matematika
    0.47
    first
    0.46
     exactement
    0.46
     primeira
    0.45
     first
    0.44
    ಥ
    0.44
     primeiras
    0.43
    Activations Density 0.002%

    No Known Activations