© 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. 90972
    Prev
    Next
    INDEX
    Explanations

    Female

    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
    Female
    -0.88
     Female
    -0.79
     female
    -0.74
     legacy
    -0.72
    FEMALE
    -0.63
    female
    -0.60
    Male
    -0.56
     Legacy
    -0.56
    legacy
    -0.54
     Male
    -0.53
    POSITIVE LOGITS
     EconPapers
    0.82
    MessageTagHelper
    0.73
     Transistor
    0.72
     ESE
    0.71
     Baillargeon
    0.71
     Cambrian
    0.70
     Ignorance
    0.69
     transistors
    0.68
     Fault
    0.66
     Puritans
    0.66
    Activations Density 0.102%

    No Known Activations