© 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. 92463
    Prev
    Next
    INDEX
    Explanations

    plea

    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
    TagHelper
    -0.56
    })()
    -0.55
    RegressionTest
    -0.54
    rungsseite
    -0.51
    ContentAlignment
    -0.49
    UnsafeEnabled
    -0.48
    falls
    -0.47
    aarrggbb
    -0.47
    InputBorder
    -0.46
    parsedMessage
    -0.46
    POSITIVE LOGITS
     needing
    0.60
     wanting
    0.57
     avoiding
    0.55
     legality
    0.55
     seeking
    0.54
     freedom
    0.54
     providing
    0.54
     rejecting
    0.54
     convenience
    0.53
     Walkover
    0.53
    Activations Density 0.002%

    No Known Activations