© 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. 93226
    Prev
    Next
    INDEX
    Explanations

    import

    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
     acost
    -0.54
    iprot
    -0.52
     ';
    -0.51
    enumii
    -0.48
    ;*/
    -0.48
     Lumb
    -0.47
     demais
    -0.45
    Identyfik
    -0.44
    _${
    -0.44
     místa
    -0.44
    POSITIVE LOGITS
    WebServlet
    0.72
    IonicModule
    0.72
    LabelTagHelper
    0.72
    PageRoute
    0.68
     InputDecoration
    0.68
    ftagPool
    0.66
    SupportActionBar
    0.65
    tonode
    0.65
    ArrowToggle
    0.65
    hloromethane
    0.64
    Activations Density 0.009%

    No Known Activations