© 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. 5-CLT-HP
    7. 93529
    Prev
    Next
    INDEX
    Explanations

    Defining identity

    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
     disambiguazione
    -0.79
     getLayout
    -0.55
    UnusedPrivate
    -0.54
     ochi
    -0.53
     BrowserModule
    -0.51
     محفوظة
    -0.50
     themselves
    -0.50
    berdayakan
    -0.50
    ाहरण
    -0.50
    ्यालय
    -0.49
    POSITIVE LOGITS
    fastjson
    0.59
    EndInit
    0.57
    makeText
    0.52
    ANSA
    0.50
    prise
    0.47
    #
    0.47
     credere
    0.46
    🍍
    0.46
    ViewById
    0.46
    loon
    0.45
    Activations Density 0.001%

    No Known Activations