© 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. 5-CLT-HP
    7. 96729
    Prev
    Next
    INDEX
    Explanations

    uncertainty or contrast

    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
    `{.
    -0.47
    val
    -0.45
     кӀош
    -0.44
     darb
    -0.43
     niv
    -0.43
    lef
    -0.43
    sal
    -0.43
    of
    -0.42
    unas
    -0.41
    şme
    -0.41
    POSITIVE LOGITS
     EconPapers
    0.70
     referenties
    0.68
    migrationBuilder
    0.68
    Xna
    0.65
    Personensuche
    0.65
    tagHelperRunner
    0.62
    twimg
    0.61
    elemField
    0.60
     GenerationType
    0.60
     كومونز
    0.59
    Activations Density 0.002%

    No Known Activations