© 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. 94070
    Prev
    Next
    INDEX
    Explanations

    energy

    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
     energy
    -1.59
    energy
    -1.45
     Energy
    -1.38
    Energy
    -1.32
     ENERGY
    -1.12
     énergétique
    -1.08
     energética
    -1.08
     energía
    -1.04
     énergie
    -1.02
     énergé
    -1.01
    POSITIVE LOGITS
     LEVEL
    0.64
     LEVELS
    0.55
     EconPapers
    0.54
    berdayakan
    0.54
    LEVEL
    0.53
     Nivel
    0.50
     level
    0.49
     source
    0.49
     Level
    0.48
    enchymal
    0.48
    Activations Density 0.153%

    No Known Activations