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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14277
    Prev
    Next
    INDEX
    Explanations

    numbers in data/code

    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
    verwijspagina
    -0.69
     myſelf
    -0.67
    expandindo
    -0.66
     blest
    -0.65
     виправивши
    -0.63
     itſelf
    -0.63
     Huguen
    -0.63
     Efq
    -0.63
     hierogly
    -0.60
     $_"
    -0.60
    POSITIVE LOGITS
     We
    0.74
     List
    0.73
      
    0.73
     Find
    0.72
     So
    0.72
     If
    0.72
     You
    0.71
     For
    0.70
     A
    0.69
     Lin
    0.69
    Activations Density 0.347%

    No Known Activations