© 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. 43498
    Prev
    Next
    INDEX
    Explanations

    promises and younger people

    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
     pledge
    -1.65
     promise
    -1.45
     pledges
    -1.45
     vow
    -1.37
     pledged
    -1.34
     Promise
    -1.30
     pledging
    -1.30
     oath
    -1.24
    promise
    -1.23
     commitments
    -1.23
    POSITIVE LOGITS
    maker
    0.56
     للمعارف
    0.56
    sticks
    0.54
    arded
    0.54
     թվական
    0.53
    load
    0.52
    ïlande
    0.50
    ock
    0.50
    evsky
    0.49
    finder
    0.49
    Activations Density 0.065%

    No Known Activations