© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95664
    Prev
    Next
    INDEX
    Explanations

    locations and events

    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
    Negative Logits
     cast
    -0.59
    i
    -0.55
    cast
    -0.54
    hoe
    -0.54
    earn
    -0.54
     climbing
    -0.53
    climbing
    -0.49
    io
    -0.49
    ex
    -0.48
    ide
    -0.47
    POSITIVE LOGITS
    CppMethod
    0.69
     ExecuteAsync
    0.68
    MessageOf
    0.68
    }{*}{}
    0.66
    Mutagenicity
    0.59
    esModule
    0.59
     مشين
    0.59
    ruptedException
    0.58
     noDo
    0.58
    études
    0.58
    Activations Density 0.100%

    No Known Activations