© 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. 0-CLT-HP
    7. 39007
    Prev
    Next
    INDEX
    Explanations

    employees and soldiers

    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
     Diſ
    -0.84
     Reſ
    -0.83
     ſeveral
    -0.82
     employees
    -0.82
     Monfieur
    -0.82
     reaſon
    -0.81
     itſelf
    -0.81
     Inſ
    -0.79
     pleaſure
    -0.75
     Conſ
    -0.75
    POSITIVE LOGITS
    fromCharCode
    0.57
    NamedQueries
    0.54
    djangoproject
    0.51
    ski
    0.50
    hips
    0.48
    ’
    0.45
    ske
    0.45
    ponses
    0.44
     Sa
    0.43
      (
    0.43
    Activations Density 0.162%

    No Known Activations