© 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. 5890
    Prev
    Next
    INDEX
    Explanations

    dates and history

    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
    vician
    -0.56
     ""],
    -0.50
     insuffisamment
    -0.50
    iac
    -0.50
    ιβ
    -0.50
    AddTagHelper
    -0.49
    EditorBrowsable
    -0.48
    DebuggerNonUser
    -0.42
    from
    -0.42
    Искәрмәләр
    -0.42
    POSITIVE LOGITS
    出版年
    0.70
    botten
    0.64
    httphttps
    0.60
    GraphicsUnit
    0.58
    enderror
    0.58
    ffles
    0.57
    ViewImports
    0.56
    :]:
    0.56
    alapa
    0.55
    tagHelperRunner
    0.54
    Activations Density 0.015%

    No Known Activations