© 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. 1-CLT-HP
    7. 15778
    Prev
    Next
    INDEX
    Explanations

    Iraq, Saudi Arabia, or medicine

    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
    FormTagHelper
    -0.50
     Arhivirano
    -0.49
     старости
    -0.47
    Hochspringen
    -0.45
    platform
    -0.45
     "..\..\
    -0.44
     HÀ
    -0.44
    Jeografia
    -0.43
     hus
    -0.43
     Wal
    -0.42
    POSITIVE LOGITS
     myſelf
    0.91
     Majefty
    0.82
     GenerationType
    0.76
     itſelf
    0.71
     pleaſure
    0.69
     Efq
    0.69
     himſelf
    0.69
     Theſe
    0.67
     themſelves
    0.66
     ſeveral
    0.66
    Activations Density 0.051%

    No Known Activations