© 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. 577
    Prev
    Next
    INDEX
    Explanations

    Locations and organizations

    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
    rungsseite
    -0.96
     zelve
    -0.94
     ویکی‌پدیا
    -0.91
    UnsafeEnabled
    -0.89
     InputDecoration
    -0.79
     nahilalakip
    -0.79
     ویکی‌پدی
    -0.77
    RectangleBorder
    -0.76
     quæ
    -0.74
     chrétien
    -0.73
    POSITIVE LOGITS
     Po
    0.52
     "
    0.52
     global
    0.48
     Bar
    0.48
     Mo
    0.47
     website
    0.46
     «
    0.46
     area
    0.46
     system
    0.45
     entry
    0.45
    Activations Density 0.463%

    No Known Activations