© 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. 15022
    Prev
    Next
    INDEX
    Explanations

    movement/mechanics

    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
    pots
    -1.32
    pot
    -1.19
    Pot
    -0.85
    POT
    -0.74
     Pot
    -0.74
     pot
    -0.73
    hol
    -0.71
     pots
    -0.61
     <<<<<<<<<<<<<<
    -0.54
    ports
    -0.54
    POSITIVE LOGITS
    yarnpkg
    0.67
     UIAlert
    0.58
     استنادى
    0.56
    AlterField
    0.56
    MigrationBuilder
    0.53
    aarrggbb
    0.53
     IConfiguration
    0.53
    contentLoaded
    0.52
     knap
    0.52
    utnik
    0.51
    Activations Density 0.135%

    No Known Activations