© 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. 5-CLT-HP
    7. 265
    Prev
    Next
    INDEX
    Explanations

    Code processing

    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
    WriteBarrier
    -0.49
    <bos>
    -0.48
    psum
    -0.46
     GIPHY
    -0.44
    ernet
    -0.44
    ens
    -0.40
    CI
    -0.40
    ITAN
    -0.39
    ALIGN
    -0.39
    IT
    -0.38
    POSITIVE LOGITS
     EconPapers
    0.88
    oredCriteria
    0.82
    urlpatterns
    0.71
     '{@
    0.70
    ditor
    0.68
     noqa
    0.65
     InputDecoration
    0.63
    цездатний
    0.63
    AddTagHelper
    0.62
     createState
    0.61
    Activations Density 0.004%

    No Known Activations