© 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. 1-CLT-HP
    7. 9565
    Prev
    Next
    INDEX
    Explanations

    holder

    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
    complexContent
    -0.73
    dotenv
    -0.60
    yntaxException
    -0.49
    holder
    -0.48
    lijkheid
    -0.45
     dormitórios
    -0.45
    Välislingid
    -0.45
    Utf
    -0.45
    iors
    -0.45
     reutiliz
    -0.44
    POSITIVE LOGITS
    }")
    0.65
    propTypes
    0.59
    PerformLayout
    0.59
     onCancelled
    0.59
    GOTREF
    0.58
     समीक्षाओं
    0.58
    ContentAsync
    0.55
     snippetHide
    0.55
    forChild
    0.54
     NSCoder
    0.54
    Activations Density 0.025%

    No Known Activations