© 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. 20-CLT-HP
    7. 71659
    Prev
    Next
    INDEX
    Explanations

    technical writing

    np_max-act-logits · 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
    Not in Any Lists

    No Comments

    Negative Logits
     automatiques
    -0.82
     chré
    -0.74
    showing
    -0.73
     Efq
    -0.72
     RIPRODUZIONE
    -0.71
     étrangère
    -0.69
     heureuse
    -0.67
     Showing
    -0.67
    umumkan
    -0.67
     exhibiting
    -0.66
    POSITIVE LOGITS
    TagMode
    0.50
     sh
    0.42
    ov
    0.40
     tur
    0.38
    ва
    0.38
     sti
    0.36
    BASEPATH
    0.35
     domin
    0.35
    は
    0.35
     over
    0.34
    Activations Density 0.000%

    No Known Activations