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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4499
    Prev
    Next
    INDEX
    Explanations

    nearness

    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
     preuves
    -1.02
     larmes
    -0.94
     investissements
    -0.94
     genoux
    -0.92
     vérit
    -0.90
     rêves
    -0.90
     épaules
    -0.89
     dieux
    -0.87
     rayures
    -0.87
     enfans
    -0.87
    POSITIVE LOGITS
     properties
    0.54
     hard
    0.45
     un
    0.43
    TRAILING
    0.42
    #![
    0.42
     cor
    0.41
     or
    0.40
     Google
    0.40
     power
    0.40
     del
    0.39
    Activations Density 0.003%

    No Known Activations