© 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. 42543
    Prev
    Next
    INDEX
    Explanations

    operate

    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
     operate
    -0.81
    cco
    -0.74
     
    -0.65
     “
    -0.55
     Of
    -0.54
    ↵
    -0.54
     As
    -0.52
     I
    -0.52
     V
    -0.52
     work
    -0.51
    POSITIVE LOGITS
    awtextra
    1.20
     Monfieur
    1.16
     Theſe
    1.10
     Anſ
    1.09
     ―――――
    1.08
     Jefus
    1.03
     myſelf
    1.02
    Hochspringen
    1.02
     itſelf
    1.01
     propOrder
    1.01
    Activations Density 0.126%

    No Known Activations