© 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. 44059
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
     a
    -0.88
     alle
    -0.59
     all
    -0.56
     alla
    -0.54
    PropertyChanging
    -0.54
     ans
    -0.53
     aan
    -0.52
     al
    -0.51
     art
    -0.51
     em
    -0.50
    POSITIVE LOGITS
     autorytatywna
    0.97
    RenderAtEndOf
    0.88
     raiſ
    0.85
     houſe
    0.85
    :✨
    0.83
     Houſe
    0.81
     Majefty
    0.80
     tfsi
    0.79
    IBarButtonItem
    0.77
     Theſe
    0.75
    Activations Density 1.570%

    No Known Activations