© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41664
    Prev
    Next
    INDEX
    Explanations

    talent

    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
     talent
    -1.05
     Talent
    -0.96
    talent
    -0.84
     talents
    -0.82
    Talent
    -0.78
     Skill
    -0.76
    Skill
    -0.73
     talentos
    -0.73
     Talents
    -0.69
     talento
    -0.68
    POSITIVE LOGITS
    fully
    0.69
    MLLoader
    0.66
    ed
    0.63
     للاسماء
    0.62
    ful
    0.60
    ัติ
    0.55
    tably
    0.54
    carteles
    0.52
     aDecoder
    0.50
    bag
    0.50
    Activations Density 1.556%

    No Known Activations