© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75812
    Prev
    Next
    INDEX
    Explanations

    Code and article snippets

    np_max-act-logits · 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
    BeginContext
    -0.73
     CreateTagHelper
    -0.66
    __':
    -0.66
    errHandler
    -0.63
     Ugo
    -0.62
    setVerticalGroup
    -0.61
    Tikang
    -0.61
    DoubleQuotes
    -0.61
    Personensuche
    -0.61
    omitempty
    -0.61
    POSITIVE LOGITS
     fast
    0.54
     s
    0.46
     swelling
    0.44
     estekak
    0.40
    Qual
    0.40
    Knowledge
    0.39
    enberg
    0.39
    Tale
    0.38
     wh
    0.38
     snippetHide
    0.38
    Activations Density 0.000%

    No Known Activations