© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 90867
    Prev
    Next
    INDEX
    Explanations

    wiring

    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
    Negative Logits
     possesso
    -0.48
     uska
    -0.47
     слу
    -0.46
    yna
    -0.44
    mem
    -0.44
    ساب
    -0.43
    SH
    -0.42
    tonsoft
    -0.42
     Flüs
    -0.42
    return
    -0.42
    POSITIVE LOGITS
    opardy
    0.68
    parsedMessage
    0.63
    posedge
    0.62
    PreferredItem
    0.59
     Paglinawan
    0.59
     EnglishChoose
    0.59
    原始内容存档于
    0.56
    ьаж
    0.56
     تضيفلها
    0.55
    ográficos
    0.55
    Activations Density 0.005%

    No Known Activations