© 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. 5-CLT-HP
    7. 98160
    Prev
    Next
    INDEX
    Explanations

    the

    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
     Cost
    -0.69
    Cost
    -0.62
     cost
    -0.61
     Costs
    -0.54
     Econom
    -0.51
     coste
    -0.51
    Costs
    -0.50
    Econom
    -0.48
     costo
    -0.48
    cost
    -0.48
    POSITIVE LOGITS
    ThroughAttribute
    0.93
     виправивши
    0.92
    ViewImports
    0.89
    AndEndTag
    0.81
    DockStyle
    0.81
     newBuilder
    0.75
    toHaveBeenCalled
    0.71
    principalTable
    0.69
    참고
    0.69
     CreateTagHelper
    0.68
    Activations Density 0.002%

    No Known Activations