© 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. 0-CLT-HP
    7. 94696
    Prev
    Next
    INDEX
    Explanations

    code, tech, foreign language

    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
     stand
    -1.36
    pers
    -1.25
     selected
    -1.17
     Stand
    -1.17
    selected
    -1.10
    Pers
    -1.05
     Pers
    -0.99
    Selected
    -0.97
     Selected
    -0.95
    stand
    -0.92
    POSITIVE LOGITS
    最快更新
    0.79
    AddTagHelper
    0.77
    LogFactory
    0.77
    новништво
    0.76
     JpaRepository
    0.76
    Rüyada
    0.76
     дописавши
    0.74
     onData
    0.71
    homonymie
    0.71
    تقاوى
    0.70
    Activations Density 0.257%

    No Known Activations