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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 44151
    Prev
    Next
    INDEX
    Explanations

    suffixes "-ly" and "-ually"

    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
    ly
    -2.00
    ually
    -1.55
    LY
    -1.55
    UALLY
    -1.01
    mente
    -0.81
    ual
    -0.79
    bly
    -0.77
    tably
    -0.77
    ualmente
    -0.76
    ably
    -0.74
    POSITIVE LOGITS
     Monfieur
    1.00
     myſelf
    0.88
     becauſe
    0.87
     Theſe
    0.84
     himſelf
    0.82
     Anſ
    0.81
     itſelf
    0.81
     againſt
    0.80
     Efq
    0.80
    SharedDtor
    0.80
    Activations Density 0.067%

    No Known Activations