© 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. 20-CLT-HP
    7. 73211
    Prev
    Next
    INDEX
    Explanations

    Forms of "to be/have"

    np_max-act-logits · 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
     Wikimedijinoj
    -0.75
    Diweddarwch
    -0.67
     betweenstory
    -0.66
    PreferredItem
    -0.60
    __':
    -0.59
     GenerationType
    -0.57
    клопе
    -0.56
    tanleria
    -0.56
     bleef
    -0.56
    verständlich
    -0.55
    POSITIVE LOGITS
     be
    1.86
     having
    0.99
     being
    0.98
     not
    0.95
     have
    0.92
     быть
    0.90
    be
    0.84
     essere
    0.84
     être
    0.82
     bein
    0.81
    Activations Density 0.002%

    No Known Activations