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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14431
    Prev
    Next
    INDEX
    Explanations

    afford

    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
     afford
    -0.82
     Afford
    -0.80
    afford
    -0.73
     affording
    -0.66
     afforded
    -0.63
     affords
    -0.59
     juridiques
    -0.56
     fört
    -0.52
    hysema
    -0.52
    goku
    -0.50
    POSITIVE LOGITS
    ably
    0.80
     تضيفلها
    0.78
     المعيارى
    0.77
     the
    0.76
     فريبيس
    0.68
    GEBURTSDATUM
    0.65
     to
    0.65
     their
    0.63
     onOptions
    0.62
     '\\;'
    0.60
    Activations Density 0.010%

    No Known Activations