© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4878
    Prev
    Next
    INDEX
    Explanations

    Technical documents and data

    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
    isi
    -0.50
    iot
    -0.50
    tising
    -0.50
    ecto
    -0.49
    mis
    -0.47
     phosphat
    -0.47
    isin
    -0.47
     incipient
    -0.47
     guilty
    -0.47
    sin
    -0.47
    POSITIVE LOGITS
    WebVitals
    0.77
    ArgumentParser
    0.75
     '\\;'
    0.75
    Geplaatst
    0.65
    Chham
    0.57
    AsUp
    0.57
     acrylique
    0.55
     Wikispecies
    0.54
    RTLI
    0.54
     fidé
    0.53
    Activations Density 0.023%

    No Known Activations