© 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. 4-CLT-HP
    7. 4401
    Prev
    Next
    INDEX
    Explanations

    and

    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
     enroll
    -0.49
     be
    -0.47
     redress
    -0.47
     deduct
    -0.46
     retire
    -0.44
     locate
    -0.44
     avoir
    -0.44
     encrypt
    -0.44
     not
    -0.42
     register
    -0.42
    POSITIVE LOGITS
     fought
    0.85
     traded
    0.83
     mastered
    0.80
     collaborated
    0.80
     danced
    0.80
     performed
    0.79
     borrowed
    0.79
     maintained
    0.79
     secured
    0.79
     tuned
    0.78
    Activations Density 0.008%

    No Known Activations