© 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. 40619
    Prev
    Next
    INDEX
    Explanations

    Att

    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
     defaultstate
    -0.65
     newOwner
    -0.60
    +#+#
    -0.59
     JAXBElement
    -0.58
    IUrlHelper
    -0.57
     jScrollPane
    -0.56
    WireFormatLite
    -0.54
     Woodlands
    -0.54
    DrawerToggle
    -0.52
    scry
    -0.52
    POSITIVE LOGITS
    GMENT
    0.51
    bomber
    0.51
    rolid
    0.49
    racing
    0.49
    ternut
    0.48
    giarism
    0.46
    otine
    0.45
    uens
    0.45
    bombs
    0.45
    $_['
    0.45
    Activations Density 0.325%

    No Known Activations