Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 70
    Prev
    Next
    INDEX
    Explanations

    helping 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
    ọa
    -0.42
    wochen
    -0.41
    venge
    -0.40
    saraba
    -0.40
    khó
    -0.39
    itchfield
    -0.39
     May
    -0.39
     Alley
    -0.38
     Hasan
    -0.38
     Beatrix
    -0.38
    POSITIVE LOGITS
    expandindo
    0.96
    psack
    0.75
     Theſe
    0.71
    MessageOf
    0.66
     SqlDbType
    0.64
     تانيه
    0.60
    CreateMap
    0.60
    extAlignment
    0.59
    ıyors
    0.57
     للمعارف
    0.57
    Activations Density 0.035%

    No Known Activations