© 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. 5-CLT-HP
    7. 94878
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    couz
    -0.50
     necess
    -0.48
     representing
    -0.48
     driven
    -0.47
     administer
    -0.45
     võ
    -0.45
     hold
    -0.44
    Vale
    -0.44
     quo
    -0.44
     ridden
    -0.44
    POSITIVE LOGITS
    EndGlobalSection
    0.76
     estekak
    0.75
     snippetHide
    0.74
    сылкі
    0.73
     kasarigan
    0.73
    ValueStyle
    0.70
    abestanden
    0.70
     lccn
    0.67
    Tikang
    0.66
    BagLayout
    0.65
    Activations Density 0.002%

    No Known Activations