© 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. 1-CLT-HP
    7. 14047
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    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
    ulemon
    -0.59
    Portály
    -0.59
    RegressionTest
    -0.58
     Majefty
    -0.58
    المناصب
    -0.58
    \}\\
    -0.57
    хьтан
    -0.57
    MessageTagHelper
    -0.56
     kasarigan
    -0.56
     photolibrary
    -0.56
    POSITIVE LOGITS
    DockStyle
    0.55
    TextAlign
    0.52
     upper
    0.49
    LAST
    0.47
    mphony
    0.45
    subpackage
    0.44
    örös
    0.44
     Lola
    0.43
    SourceChecksum
    0.42
     last
    0.42
    Activations Density 0.021%

    No Known Activations