© 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. 46087
    Prev
    Next
    INDEX
    Explanations

    piano

    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
    ering
    -0.45
    ichord
    -0.43
    mite
    -0.41
    photo
    -0.40
    picture
    -0.40
    body
    -0.40
    na
    -0.40
    ity
    -0.40
    way
    -0.40
    fellow
    -0.40
    POSITIVE LOGITS
     propOrder
    0.94
     ModelExpression
    0.81
    MigrationBuilder
    0.78
    NameInMap
    0.73
    sizeCache
    0.73
     архивлан
    0.72
    WriteTagHelper
    0.71
     '{@
    0.68
    AddTagHelper
    0.67
    ButterKnife
    0.66
    Activations Density 0.007%

    No Known Activations