© 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. 0-CLT-HP
    7. 40731
    Prev
    Next
    INDEX
    Explanations

    uncommon text

    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
     ComVisible
    -0.90
     unknownFields
    -0.88
     esternos
    -0.84
    '))
    -0.83
    queryInterface
    -0.82
     Taktlose
    -0.79
    WireFormatLite
    -0.77
     purpoſe
    -0.75
    nastics
    -0.74
    principalTable
    -0.74
    POSITIVE LOGITS
    i
    0.75
    a
    0.62
    e
    0.61
    й
    0.57
    ec
    0.54
     аппетита
    0.51
    ed
    0.50
    o
    0.50
    et
    0.50
    I
    0.50
    Activations Density 0.112%

    No Known Activations