© 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. 20-CLT-HP
    7. 75449
    Prev
    Next
    INDEX
    Explanations

    predictors

    np_max-act-logits · 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
    posedge
    -0.65
    RegressionTest
    -0.62
    tvguidetime
    -0.60
    MigrationBuilder
    -0.55
     Signalez
    -0.55
     CURIAM
    -0.53
     rapports
    -0.52
    RenderAtEndOf
    -0.52
     PLWABN
    -0.50
    XtraReports
    -0.49
    POSITIVE LOGITS
     BrowserModule
    0.74
     Houſe
    0.59
     houſe
    0.58
    kuuta
    0.55
     preſent
    0.52
     <>",
    0.51
    otoro
    0.51
     Lordships
    0.49
    Datuak
    0.49
    적으로
    0.49
    Activations Density 0.000%

    No Known Activations