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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40685
    Prev
    Next
    INDEX
    Explanations

    who

    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
     who
    -1.28
    who
    -1.05
    Who
    -0.79
     Who
    -0.78
     whom
    -0.75
     quien
    -0.71
     whose
    -0.58
     quem
    -0.54
     którzy
    -0.54
     siapa
    -0.53
    POSITIVE LOGITS
     snippetHide
    1.05
    PerformLayout
    0.88
    PreferredItem
    0.88
     referenties
    0.84
    RenderAtEndOf
    0.84
     JpaRepository
    0.83
     GenerationType
    0.79
     محفوظة
    0.79
     مشين
    0.79
    Obrázky
    0.77
    Activations Density 0.067%

    No Known Activations