© 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. 39900
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives

    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
    larger
    -1.95
    bigger
    -1.95
    Larger
    -1.90
     coarser
    -1.88
     Larger
    -1.84
     bigger
    -1.80
     heavier
    -1.80
     louder
    -1.80
    smaller
    -1.80
     thicker
    -1.78
    POSITIVE LOGITS
     than
    1.17
     and
    1.00
     (
    0.94
    ,
    0.93
     
    0.86
     in
    0.76
     then
    0.76
    /
    0.73
     or
    0.73
     "
    0.72
    Activations Density 0.517%

    No Known Activations