© 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. 42468
    Prev
    Next
    INDEX
    Explanations

    supplemented

    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
     supplemented
    -0.72
    aided
    -0.63
    lemented
    -0.63
    supplement
    -0.62
     supplementing
    -0.62
     supplemental
    -0.60
     spéciaux
    -0.58
     supplement
    -0.57
    Supplement
    -0.56
    ing
    -0.56
    POSITIVE LOGITS
     itſelf
    0.75
     myſelf
    0.59
     Jefus
    0.57
    JsonFormat
    0.57
    ParallelGroup
    0.56
     Савезне
    0.55
     chofe
    0.54
    (;;)
    0.54
     defire
    0.54
     obfer
    0.54
    Activations Density 0.783%

    No Known Activations