© 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. 9544
    Prev
    Next
    INDEX
    Explanations

    supply

    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
     supply
    -0.58
    Supply
    -0.53
     Supply
    -0.52
    supply
    -0.49
     secondaires
    -0.49
    SUPPLY
    -0.47
     között
    -0.46
     sommeil
    -0.46
    TagHelper
    -0.46
     pernas
    -0.46
    POSITIVE LOGITS
     Roskov
    0.68
     autorytatywna
    0.66
     ashore
    0.59
     Waray
    0.59
     basalt
    0.58
     depic
    0.57
     Illus
    0.55
    Personendaten
    0.55
     adjuvant
    0.55
     الاطلاع
    0.54
    Activations Density 0.004%

    No Known Activations