© 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. 10037
    Prev
    Next
    INDEX
    Explanations

    the

    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
     CreateTagHelper
    -0.64
     estekak
    -0.62
     wikipagina
    -0.61
    Zunanje
    -0.61
    TagMode
    -0.59
     adultes
    -0.56
     chiamata
    -0.54
    存于互联网档案馆
    -0.53
    Читати
    -0.52
     utveckling
    -0.52
    POSITIVE LOGITS
     nature
    0.78
    nextDouble
    0.59
    DockStyle
    0.59
     durability
    0.58
     likelihood
    0.56
     reasonableness
    0.56
     type
    0.56
     robustness
    0.55
     practicality
    0.54
     most
    0.54
    Activations Density 0.016%

    No Known Activations