© 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. 1-CLT-HP
    7. 10864
    Prev
    Next
    INDEX
    Explanations

    home

    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
    Hauptartikel
    -0.54
     jScrollPane
    -0.54
     оригіналу
    -0.52
     propOrder
    -0.51
    featureID
    -0.51
    PageRoute
    -0.50
    WebElementEntity
    -0.50
     INTERESAR
    -0.50
     Logement
    -0.48
     home
    -0.47
    POSITIVE LOGITS
    DockStyle
    0.61
    o
    0.58
    ostatic
    0.53
    onomic
    0.52
    oster
    0.50
     Metab
    0.50
    WireFormatLite
    0.49
    odo
    0.48
    obe
    0.48
    pty
    0.47
    Activations Density 0.014%

    No Known Activations