© 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. 39829
    Prev
    Next
    INDEX
    Explanations

    verbs ending in "ing"

    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
     Jefus
    -1.67
     Theſe
    -1.66
     Monfieur
    -1.62
     myſelf
    -1.59
     purpoſe
    -1.58
     pleaſure
    -1.50
     Majefty
    -1.49
     ſeveral
    -1.47
     Anſ
    -1.44
     itſelf
    -1.44
    POSITIVE LOGITS
     of
    1.70
     in
    0.86
     at
    0.68
     so
    0.66
     on
    0.65
     
    0.65
     with
    0.63
     for
    0.61
     l
    0.61
     L
    0.60
    Activations Density 0.240%

    No Known Activations