© 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. 94405
    Prev
    Next
    INDEX
    Explanations

    then

    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
     vectorstock
    -0.66
     themſelves
    -0.65
     ſmall
    -0.63
     pngtree
    -0.63
     bestaan
    -0.62
    UnifiedTopology
    -0.62
    transQ
    -0.61
     bestehen
    -0.60
    eridge
    -0.60
     enfans
    -0.60
    POSITIVE LOGITS
     uses
    0.88
     has
    0.87
     begins
    0.86
     goes
    0.84
     gets
    0.83
     carries
    0.82
     plays
    0.81
     develops
    0.81
     does
    0.79
     extends
    0.79
    Activations Density 0.034%

    No Known Activations