© 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. 91986
    Prev
    Next
    INDEX
    Explanations

    code

    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
    KommentareTeilen
    -0.66
    InitVars
    -0.56
     nakalista
    -0.52
    InstrumentedTest
    -0.51
    Билгалдахарш
    -0.49
    TryParse
    -0.47
    stus
    -0.47
    thanes
    -0.47
    AddTagHelper
    -0.47
    Erreferentziak
    -0.47
    POSITIVE LOGITS
    ValueStyle
    0.78
    ixante
    0.70
    tvguidetime
    0.63
    клопе
    0.56
    djangoproject
    0.54
     EconPapers
    0.53
    LayoutStyle
    0.52
    saraba
    0.49
    帖最后由
    0.48
    wijl
    0.48
    Activations Density 0.007%

    No Known Activations