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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91276
    Prev
    Next
    INDEX
    Explanations

    atta

    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
    atta
    -1.64
    atte
    -0.87
     Perkins
    -0.87
     propOrder
    -0.74
    Atta
    -0.67
     atta
    -0.62
     Attached
    -0.61
    Attached
    -0.60
     Atta
    -0.55
     attach
    -0.47
    POSITIVE LOGITS
    webElementXpaths
    0.67
     betweenstory
    0.65
     myſelf
    0.59
    y
    0.58
     pennies
    0.58
    estyles
    0.56
    yntaxException
    0.55
     himſelf
    0.55
    outons
    0.54
     ***!
    0.53
    Activations Density 0.110%

    No Known Activations