© 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. 5-CLT-HP
    7. 5999
    Prev
    Next
    INDEX
    Explanations

    only

    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
     prochaine
    -0.62
     prochaines
    -0.58
     gevolg
    -0.53
     relève
    -0.52
    ContentAsync
    -0.52
     considér
    -0.51
    
    -0.51
     financières
    -0.50
     &___
    -0.50
     vectorielles
    -0.50
    POSITIVE LOGITS
     quality
    0.67
    %"),
    0.62
     ModelExpression
    0.59
     proven
    0.56
     prime
    0.55
     /\.(
    0.55
    }`}
    0.54
     reputable
    0.52
    "];
    0.52
     unmarked
    0.51
    Activations Density 0.004%

    No Known Activations