© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75792
    Prev
    Next
    INDEX
    Explanations

    research papers

    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
    tagHelperRunner
    -0.66
    ajuku
    -0.60
    पाद
    -0.58
     EDITOR
    -0.56
    ersachsen
    -0.56
     Lordships
    -0.56
    tagext
    -0.55
     كومونز
    -0.54
     Paar
    -0.53
    aderas
    -0.53
    POSITIVE LOGITS
     West
    0.56
    ArrowToggle
    0.50
     województwie
    0.49
    urlpatterns
    0.48
     ModelExpression
    0.46
    West
    0.45
    adaptiveStyles
    0.43
     Wab
    0.43
    таратура
    0.42
    pielt
    0.41
    Activations Density 0.005%

    No Known Activations