© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92918
    Prev
    Next
    INDEX
    Explanations

    to

    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
     and
    -0.95
     or
    -0.51
    pumpe
    -0.49
    شنبه
    -0.43
     control
    -0.43
    asion
    -0.41
    rildi
    -0.40
     surla
    -0.40
    Itoa
    -0.40
    marshaller
    -0.40
    POSITIVE LOGITS
    uxxxx
    0.75
     geologists
    0.72
    BufferException
    0.70
     Bartholomew
    0.70
     Messina
    0.70
     astronomers
    0.69
     Mahomet
    0.69
     Constantine
    0.69
    esModule
    0.69
     archaeologists
    0.68
    Activations Density 0.003%

    No Known Activations