© 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. 4-CLT-HP
    7. 2842
    Prev
    Next
    INDEX
    Explanations

    the

    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
     surla
    -0.87
     kasarigan
    -0.81
     myſelf
    -0.76
    RegressionTest
    -0.75
     Efq
    -0.72
    assertRaises
    -0.71
     Portail
    -0.70
     houſe
    -0.69
     '\\;'
    -0.69
     preſent
    -0.68
    POSITIVE LOGITS
     time
    0.51
    .
    0.44
     OFDb
    0.43
    Eloquent
    0.43
     steps
    0.41
    right
    0.41
     up
    0.40
    таратура
    0.40
    )
    0.39
    i
    0.39
    Activations Density 0.002%

    No Known Activations