© 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. 95714
    Prev
    Next
    INDEX
    Explanations

    I

    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
    CloseOperation
    -0.73
    sprogramm
    -0.50
    viewDidLoad
    -0.49
    tvguidetime
    -0.49
    
    -0.47
     resourceCulture
    -0.46
    addPreferredGap
    -0.44
    bildschirm
    -0.44
     disambiguazione
    -0.44
    
    -0.44
    POSITIVE LOGITS
     Assyrian
    0.63
     lordship
    0.59
     Persians
    0.58
     Protestantism
    0.57
     Byzantium
    0.57
     Christendom
    0.56
     Judah
    0.55
     Arjuna
    0.54
     Whigs
    0.53
     Doğ
    0.53
    Activations Density 0.017%

    No Known Activations