© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90712
    Prev
    Next
    INDEX
    Explanations

    exception

    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
     exception
    -1.70
     exceptions
    -1.58
    exception
    -1.40
     Exceptions
    -1.39
     EXCEPT
    -1.38
     excepted
    -1.34
     excludes
    -1.33
     exclusions
    -1.30
    EXCEPT
    -1.30
     exclude
    -1.29
    POSITIVE LOGITS
     
    0.69
    ally
    0.59
     (
    0.58
     “
    0.58
     the
    0.58
     for
    0.57
     an
    0.54
     of
    0.54
     Al
    0.54
     a
    0.54
    Activations Density 0.069%

    No Known Activations