© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38309
    Prev
    Next
    INDEX
    Explanations

    importance necessity

    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
     a
    -0.57
     an
    -0.56
     his
    -0.54
     U
    -0.52
     in
    -0.52
    richTextPanel
    -0.51
     man
    -0.50
    tabular
    -0.49
     so
    -0.48
     H
    -0.47
    POSITIVE LOGITS
    Tē
    0.78
     étrangère
    0.75
     Necessity
    0.73
     africains
    0.72
     AssemblyCulture
    0.72
     Convey
    0.72
     japonaise
    0.71
     auffi
    0.71
     hearers
    0.71
     épis
    0.71
    Activations Density 1.622%

    No Known Activations