© 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. 91987
    Prev
    Next
    INDEX
    Explanations

    boy, girl, Victorian, Victoria

    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
     boy
    -0.85
     Boy
    -0.82
     BOY
    -0.79
     Girl
    -0.71
     Victoria
    -0.71
    CloseOperation
    -0.69
    Victoria
    -0.69
    Boy
    -0.66
     GIRL
    -0.63
    AccessorTable
    -0.63
    POSITIVE LOGITS
     StatefulWidget
    0.56
     Returns
    0.54
    tvguidetime
    0.53
    friend
    0.50
     Guests
    0.50
     degrés
    0.49
    JspWriter
    0.48
     Pluto
    0.48
     Euphrates
    0.48
    hdessä
    0.47
    Activations Density 0.031%

    No Known Activations