© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92569
    Prev
    Next
    INDEX
    Explanations

    technical/scientific context

    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
     memperhatikan
    -0.62
    hatikan
    -0.59
     внимательно
    -0.57
     Carefully
    -0.55
     uwagę
    -0.53
     sorgfältig
    -0.53
     carefully
    -0.52
     sorgfäl
    -0.51
    Careful
    -0.50
     nôtre
    -0.50
    POSITIVE LOGITS
    protoimpl
    0.79
    GEBURTSDATUM
    0.76
     незавершена
    0.72
    IUrlHelper
    0.70
    ReusableCell
    0.68
    expandindo
    0.65
    TypedDataSet
    0.63
    ChildScrollView
    0.61
    TestingModule
    0.60
     مرئيه
    0.57
    Activations Density 0.003%

    No Known Activations