© 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. 5-CLT-HP
    7. 1155
    Prev
    Next
    INDEX
    Explanations

    refusing

    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
     appunto
    -0.64
    tagext
    -0.59
    ConfigureAwait
    -0.54
    PRNewswire
    -0.52
    ViewImports
    -0.52
    zow
    -0.50
    wpi
    -0.50
     venons
    -0.50
     dedans
    -0.50
    AsUp
    -0.49
    POSITIVE LOGITS
     sex
    0.52
     friendship
    0.49
    ✨:
    0.48
    SuccessListener
    0.48
    AnchorStyles
    0.48
    ReusableCell
    0.47
     food
    0.46
    <bos>
    0.45
     eating
    0.44
     helping
    0.44
    Activations Density 0.003%

    No Known Activations