© 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. 43792
    Prev
    Next
    INDEX
    Explanations

    be

    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
     be
    -2.00
    be
    -1.12
     Be
    -1.04
    Be
    -0.97
     soient
    -0.94
     puissent
    -0.90
     puisse
    -0.85
     BE
    -0.84
     coû
    -0.83
     быть
    -0.82
    POSITIVE LOGITS
     counted
    0.69
    Personendaten
    0.68
     considered
    0.67
     able
    0.66
     awarded
    0.66
     greeted
    0.66
     sentenced
    0.66
     accorded
    0.65
     saluted
    0.65
     entrusted
    0.65
    Activations Density 0.265%

    No Known Activations