© 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. 40581
    Prev
    Next
    INDEX
    Explanations

    "to be" verbs

    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
     skydd
    -0.50
     aspetta
    -0.49
     julk
    -0.49
     conosce
    -0.48
     sebaiknya
    -0.47
     originais
    -0.46
     kohta
    -0.45
     debole
    -0.44
     aasta
    -0.44
    bbene
    -0.43
    POSITIVE LOGITS
    ArgsConstructor
    0.87
    RectangleBorder
    0.87
    esez
    0.86
    extAlignment
    0.86
    存于互联网档案馆
    0.82
    rolid
    0.79
    tvguidetime
    0.79
    verwijspagina
    0.77
    complexContent
    0.77
    Personensuche
    0.77
    Activations Density 0.036%

    No Known Activations