© 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. 5-CLT-HP
    7. 96071
    Prev
    Next
    INDEX
    Explanations

    gender

    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
     male
    -0.83
     Male
    -0.81
    Male
    -0.79
     gender
    -0.79
    Female
    -0.79
     Female
    -0.78
    Gender
    -0.76
     Gender
    -0.74
    female
    -0.73
     female
    -0.71
    POSITIVE LOGITS
    coledì
    0.54
    UnsafeEnabled
    0.50
    격
    0.49
     emotionally
    0.47
    UrlResolution
    0.47
    sible
    0.47
     Testa
    0.46
    FRI
    0.45
     desem
    0.45
    Economia
    0.44
    Activations Density 0.001%

    No Known Activations