© 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. 92752
    Prev
    Next
    INDEX
    Explanations

    IPO and equality

    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
    IPO
    -0.85
     equally
    -0.83
    quelize
    -0.64
     endorsed
    -0.57
     IPO
    -0.55
    MessageTagHelper
    -0.50
    houses
    -0.48
    iver
    -0.47
     mouths
    -0.46
    omock
    -0.45
    POSITIVE LOGITS
    ReusableCell
    0.79
    WebElementEntity
    0.76
    ImageContext
    0.71
     disambiguazione
    0.70
    XmlAccessType
    0.68
    SequentialGroup
    0.67
     estekak
    0.67
     مرئيه
    0.67
    WithIOException
    0.67
    GEBURTSDATUM
    0.66
    Activations Density 1.215%

    No Known Activations