© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41308
    Prev
    Next
    INDEX
    Explanations

    towers and centers

    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
     centers
    -1.09
     centres
    -1.07
     Centers
    -1.05
    centers
    -0.91
     Centres
    -0.86
     Towers
    -0.84
     towers
    -0.81
    Centers
    -0.81
    mergeFrom
    -0.79
    ReusableCell
    -0.69
    POSITIVE LOGITS
    ponses
    0.50
    uolo
    0.50
    undur
    0.50
    setupUi
    0.49
     préféré
    0.48
    яд
    0.48
    Royce
    0.45
     Sieger
    0.44
     mencu
    0.44
     forties
    0.44
    Activations Density 0.045%

    No Known Activations