© 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. 95069
    Prev
    Next
    INDEX
    Explanations

    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
    aarrggbb
    -0.90
     '\\;'
    -0.78
    SequentialGroup
    -0.74
     asiatique
    -0.72
    travel
    -0.71
     propagate
    -0.70
     travel
    -0.69
    efforts
    -0.69
     الاطلاع
    -0.69
     propagated
    -0.68
    POSITIVE LOGITS
     c
    0.43
    atorship
    0.42
    hog
    0.41
     officio
    0.41
    s
    0.41
    ucar
    0.40
    abank
    0.40
    self
    0.39
    .
    0.39
    shirt
    0.39
    Activations Density 0.034%

    No Known Activations