© 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. 9491
    Prev
    Next
    INDEX
    Explanations

    resting

    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
    an
    -0.57
    y
    -0.54
     ägg
    -0.52
     Kombat
    -0.52
     Auto
    -0.52
     KNIGHT
    -0.50
    gy
    -0.50
    nytt
    -0.49
     SwiftUI
    -0.49
    er
    -0.48
    POSITIVE LOGITS
    Diwedd
    0.66
    ########.
    0.61
    :✨
    0.59
    GOTREF
    0.54
    хьтан
    0.53
    BindView
    0.50
     Италијани
    0.48
     mula
    0.48
     Baillargeon
    0.48
    "}")
    0.48
    Activations Density 0.032%

    No Known Activations