© 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. 94959
    Prev
    Next
    INDEX
    Explanations

    variety of internet text

    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
    even
    -0.94
     even
    -0.89
    Even
    -0.78
     Even
    -0.77
     persino
    -0.68
     siquiera
    -0.66
     EVEN
    -0.66
     даже
    -0.65
     même
    -0.65
     AppCompat
    -0.65
    POSITIVE LOGITS
     GIPHY
    0.66
     Genocide
    0.60
    astify
    0.57
    addGap
    0.56
     Obispo
    0.55
     sapi
    0.55
    SBATCH
    0.54
    ttino
    0.54
    getRuntime
    0.54
    %");
    0.54
    Activations Density 1.658%

    No Known Activations