© 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. 6143
    Prev
    Next
    INDEX
    Explanations

    time

    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
     that
    -0.62
    netinet
    -0.50
     bahawa
    -0.48
    DidLoad
    -0.47
     yılı
    -0.47
    __':
    -0.47
    Diweddarwch
    -0.47
     valign
    -0.47
    Handlung
    -0.46
    istiwa
    -0.45
    POSITIVE LOGITS
     صوتيه
    0.56
    endpush
    0.55
    gdx
    0.54
    StoryboardSegue
    0.53
    modelBuilder
    0.53
    buttonBar
    0.52
    FunctionFlags
    0.52
    RectangleBorder
    0.51
    Gizmos
    0.50
    tagHelper
    0.49
    Activations Density 0.002%

    No Known Activations