© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92822
    Prev
    Next
    INDEX
    Explanations

    jet

    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
     jet
    -0.67
     rocket
    -0.66
     Funding
    -0.63
     Rocket
    -0.61
     Jet
    -0.58
    jet
    -0.58
     funding
    -0.57
     satellite
    -0.57
    Funding
    -0.57
     Reef
    -0.56
    POSITIVE LOGITS
    PerformLayout
    0.76
     whoſe
    0.69
    ViewImports
    0.69
    期刊论文
    0.66
     themſelves
    0.61
     Efq
    0.60
    MLLoader
    0.60
    reactstrap
    0.59
     againſt
    0.58
    aarrggbb
    0.58
    Activations Density 0.409%

    No Known Activations