© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95748
    Prev
    Next
    INDEX
    Explanations

    executing

    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
    Negative Logits
     Executed
    -1.15
     executing
    -1.09
     Anſ
    -1.07
     doubtnut
    -1.04
     Execute
    -1.03
     executes
    -1.03
    Execute
    -1.02
     Theſe
    -1.02
     ſeveral
    -1.01
     Execution
    -1.00
    POSITIVE LOGITS
     
    0.62
    ,
    0.62
    ↵↵
    0.61
     (
    0.60
     in
    0.59
     and
    0.59
     or
    0.57
    ↵
    0.57
    /
    0.56
     b
    0.54
    Activations Density 0.119%

    No Known Activations