© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90696
    Prev
    Next
    INDEX
    Explanations

    equilibrium

    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
     equilibrium
    -0.76
     balance
    -0.68
     équilibre
    -0.65
     Equilibrium
    -0.65
     external
    -0.62
     väli
    -0.61
     Moscou
    -0.60
     External
    -0.60
     equilibrio
    -0.60
     HasFactory
    -0.60
    POSITIVE LOGITS
    disposing
    0.54
    OCCURRED
    0.54
    penup
    0.54
     phase
    0.52
     hairs
    0.49
     phases
    0.48
    новништво
    0.48
     zvuky
    0.47
     whor
    0.45
     behind
    0.45
    Activations Density 0.065%

    No Known Activations