© 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. 1218
    Prev
    Next
    INDEX
    Explanations

    Avoid

    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
     avoided
    -1.28
     Avoid
    -1.18
     Avoidance
    -1.18
     avoidance
    -1.14
     avoid
    -1.13
    Avoid
    -1.09
    avoid
    -1.07
     avoids
    -1.03
     Avoiding
    -0.99
     avoiding
    -0.98
    POSITIVE LOGITS
     being
    0.61
     it
    0.56
    enumi
    0.55
    UIControlState
    0.53
     all
    0.51
     re
    0.46
     
    0.44
     inf
    0.44
     pas
    0.43
     https
    0.43
    Activations Density 0.058%

    No Known Activations