© 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. 16057
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
    WebVitals
    -0.85
    addContainerGap
    -0.81
     defaultstate
    -0.74
    AddTagHelper
    -0.73
    CloseOperation
    -0.70
     linkovi
    -0.69
    Datuak
    -0.69
    ंदीखरीदारी
    -0.68
    +#+#
    -0.68
    OGND
    -0.68
    POSITIVE LOGITS
    jęt
    0.45
    etsk
    0.43
     calculées
    0.43
     tenue
    0.39
    وزی
    0.38
    felt
    0.38
    سخ
    0.38
    mtrl
    0.38
     ospiti
    0.37
    pejo
    0.36
    Activations Density 0.058%

    No Known Activations