© 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. 4-CLT-HP
    7. 520
    Prev
    Next
    INDEX
    Explanations

    Code/data snippets

    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
    SpringBootTest
    -0.64
    Palmarès
    -0.58
    دانشنامهٔ
    -0.57
     EconPapers
    -0.56
    makeText
    -0.55
    ValueStyle
    -0.55
    GOTREF
    -0.54
    RenderAtEndOf
    -0.54
    Izvori
    -0.54
    存于互联网档案馆
    -0.52
    POSITIVE LOGITS
    ISupport
    0.59
    Espèce
    0.51
     createSprite
    0.50
    uality
    0.50
    occupe
    0.49
    IGraphics
    0.48
     coals
    0.48
     sabbia
    0.47
     marins
    0.47
     partag
    0.47
    Activations Density 0.002%

    No Known Activations