© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 637
    Prev
    Next
    INDEX
    Explanations

    Dy or Rad

    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
     Dy
    -0.66
     intptr
    -0.52
    Dy
    -0.50
    setPixel
    -0.47
    FieldBuilder
    -0.47
    TagHelpers
    -0.47
    esgue
    -0.46
     通販
    -0.45
    aita
    -0.44
    otomy
    -0.44
    POSITIVE LOGITS
    躇
    0.62
    aarrggbb
    0.58
     mergeFrom
    0.56
     Réponses
    0.54
     AssemblyCulture
    0.54
    SequentialGroup
    0.52
    __':
    0.52
    ScopeManager
    0.52
     Lorena
    0.51
     calendriers
    0.51
    Activations Density 0.018%

    No Known Activations