© 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. 15833
    Prev
    Next
    INDEX
    Explanations

    air travel

    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
    ]--;
    -0.68
    MessageTagHelper
    -0.62
    jsxFileName
    -0.62
    WriteTagHelper
    -0.59
    ANTLR
    -0.56
     resourceCulture
    -0.54
    ünkü
    -0.53
    multer
    -0.52
    rungsseite
    -0.52
     DbType
    -0.52
    POSITIVE LOGITS
    mius
    0.55
    sillos
    0.48
    Statistiche
    0.47
    mering
    0.47
    ness
    0.47
     flank
    0.46
     market
    0.46
     markets
    0.46
    sillo
    0.46
    istik
    0.45
    Activations Density 0.048%

    No Known Activations