© 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. 43068
    Prev
    Next
    INDEX
    Explanations

    Airports/Runways and Andrews

    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
    ness
    -0.82
    nesses
    -0.59
    ning
    -0.56
     Kennedy
    -0.56
    ALIAN
    -0.54
    nes
    -0.54
    amation
    -0.53
    nis
    -0.52
    apunov
    -0.52
    nies
    -0.51
    POSITIVE LOGITS
     itſelf
    0.90
     Theſe
    0.81
     becauſe
    0.79
     Jefus
    0.75
     houſe
    0.73
     whoſe
    0.73
     ſhe
    0.71
     ſeveral
    0.71
     themſelves
    0.70
     myſelf
    0.69
    Activations Density 1.060%

    No Known Activations