© 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. 91030
    Prev
    Next
    INDEX
    Explanations

    0 and 5

    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
    ¼
    -0.64
    __':
    -0.62
    __':
    -0.59
     allmän
    -0.59
     églises
    -0.58
    URLException
    -0.56
     ¾
    -0.56
     Romains
    -0.55
     étrangères
    -0.54
     chré
    -0.54
    POSITIVE LOGITS
    HasAnnotation
    0.61
    хьтан
    0.57
     lenker
    0.57
     referenties
    0.56
    StoryboardSegue
    0.54
     pinulongan
    0.54
    Externé
    0.52
    Geplaatst
    0.50
    OrNil
    0.49
    Controllo
    0.49
    Activations Density 0.005%

    No Known Activations