© 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. 0-CLT-HP
    7. 43187
    Prev
    Next
    INDEX
    Explanations

    revealing something

    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
     Index
    -0.79
     Free
    -0.72
     Arena
    -0.65
     tension
    -0.63
    INDEX
    -0.61
    Index
    -0.60
     Tension
    -0.59
     arena
    -0.58
    Tension
    -0.57
    EOUS
    -0.57
    POSITIVE LOGITS
     wireType
    0.73
     nakalista
    0.69
    AxisAlignment
    0.68
    HtmlAttribute
    0.66
     Paglinawan
    0.66
    tagHelperRunner
    0.65
    ViewFeatures
    0.65
     autorytatywna
    0.62
     متعلقه
    0.59
    ArrowToggle
    0.58
    Activations Density 0.104%

    No Known Activations