© 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. 5-CLT-HP
    7. 94716
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Viitteet
    -0.82
    Sucesor
    -0.82
     ویکی‌پدیای
    -0.75
    bbene
    -0.73
     AspNetCore
    -0.71
    transQ
    -0.70
     kasarigan
    -0.69
    PhysRev
    -0.69
     createState
    -0.67
     оригіналу
    -0.66
    POSITIVE LOGITS
     doInBackground
    0.43
     du
    0.42
    graphql
    0.39
    AddWithValue
    0.38
    iostream
    0.38
    ียด
    0.37
     benefic
    0.36
     client
    0.36
     useful
    0.35
    AddTagHelper
    0.35
    Activations Density 0.070%

    No Known Activations