© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92739
    Prev
    Next
    INDEX
    Explanations

    conflicts and political situations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.84
     initComponents
    -0.74
    httphttps
    -0.73
    ьаж
    -0.72
    اث
    -0.64
    aarrggbb
    -0.64
     ExecuteAsync
    -0.61
    KommentareTeilen
    -0.61
    dero
    -0.57
     CreateTagHelper
    -0.57
    POSITIVE LOGITS
    oł
    0.57
     deal
    0.54
    częściej
    0.52
    InjectAttribute
    0.50
    NamedQuery
    0.46
    postDelayed
    0.46
     agreement
    0.44
    tragen
    0.44
    Groovy
    0.43
    QUADS
    0.43
    Activations Density 0.000%

    No Known Activations