© 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. 13254
    Prev
    Next
    INDEX
    Explanations

    news

    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
    withstanding
    -0.50
    MLLoader
    -0.49
    ectoria
    -0.47
    encodeWith
    -0.45
    تمبر
    -0.45
    География
    -0.43
    جمعیت
    -0.41
    êmica
    -0.41
    kiwa
    -0.41
     ""],
    -0.41
    POSITIVE LOGITS
    ngdoc
    0.86
    jooq
    0.63
    MigrationBuilder
    0.63
    RegressionTest
    0.59
     transfieras
    0.57
    gdx
    0.57
    StoryboardSegue
    0.57
    attraction
    0.56
     OFDb
    0.56
    essive
    0.55
    Activations Density 0.014%

    No Known Activations