© 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. 1-CLT-HP
    7. 10298
    Prev
    Next
    INDEX
    Explanations

    to

    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
     be
    -0.80
     make
    -0.75
     get
    -0.73
     do
    -0.71
     put
    -0.71
     bring
    -0.69
     look
    -0.66
     have
    -0.63
     take
    -0.63
     offer
    -0.63
    POSITIVE LOGITS
     ſeveral
    1.08
     Majefty
    1.06
     $_"
    1.05
     poffible
    1.05
     Efq
    1.04
     iſt
    1.02
     itſelf
    0.99
     Monfieur
    0.94
     Jefus
    0.93
     Chriſt
    0.92
    Activations Density 0.034%

    No Known Activations