© 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. 43195
    Prev
    Next
    INDEX
    Explanations

    do

    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
     evacuate
    -0.78
     do
    -0.73
     survie
    -0.72
     fluence
    -0.69
     uſe
    -0.68
     ſtand
    -0.68
     evaporate
    -0.67
     fhew
    -0.66
     thermoc
    -0.66
     astronauts
    -0.66
    POSITIVE LOGITS
    ="#">
    0.54
    %">
    0.48
     Sur
    0.47
    *}\
    0.47
     Har
    0.46
    ()},
    0.46
    cual
    0.46
     this
    0.45
     */
    0.45
    ="">
    0.45
    Activations Density 0.067%

    No Known Activations