© 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. 8898
    Prev
    Next
    INDEX
    Explanations

    as

    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
    šech
    -0.49
     références
    -0.49
    言うと
    -0.41
     hanya
    -0.41
     bParam
    -0.40
     were
    -0.40
    gänger
    -0.40
    <bos>
    -0.40
    vikle
    -0.39
     humanidade
    -0.39
    POSITIVE LOGITS
     such
    1.20
    such
    1.01
    Such
    1.00
     Such
    0.90
     SUCH
    0.85
     sådan
    0.80
     solche
    0.77
    matically
    0.73
    pires
    0.71
     solchen
    0.71
    Activations Density 0.127%

    No Known Activations