© 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. 1-CLT-HP
    7. 8632
    Prev
    Next
    INDEX
    Explanations

    among

    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
     IDisposable
    -0.54
    jalá
    -0.52
     bébés
    -0.50
     préfé
    -0.50
     obé
    -0.49
     orizz
    -0.48
     emporter
    -0.47
     fallu
    -0.47
     صوتيه
    -0.46
     réfugi
    -0.46
    POSITIVE LOGITS
    DoubleQuotes
    0.73
    principalTable
    0.71
    AccessFile
    0.60
    soever
    0.59
    /*:
    0.57
     considérons
    0.57
     nonatomic
    0.56
    opat
    0.56
    TagHelper
    0.54
    ChangeListener
    0.54
    Activations Density 0.012%

    No Known Activations