© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 5063
    Prev
    Next
    INDEX
    Explanations

    of

    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
     course
    -0.60
    course
    -0.51
    Course
    -0.44
     Afghans
    -0.42
     COURSE
    -0.42
    resenta
    -0.40
     Course
    -0.40
    徒
    -0.40
     corse
    -0.39
     acordo
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    0.72
     kasarigan
    0.67
    protoimpl
    0.65
    rostis
    0.63
    fjspx
    0.63
    transQ
    0.61
     defaultstate
    0.60
     Италијани
    0.60
     חיצוניים
    0.60
    enseits
    0.59
    Activations Density 0.004%

    No Known Activations