© 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. 1-CLT-HP
    7. 10018
    Prev
    Next
    INDEX
    Explanations

    thing

    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
     escape
    -0.69
     Escape
    -0.62
    escape
    -0.60
     escapes
    -0.57
     ESCAPE
    -0.56
    Escape
    -0.53
     domésticos
    -0.49
    wau
    -0.47
    oui
    -0.46
    oznam
    -0.45
    POSITIVE LOGITS
    PerformLayout
    0.88
     HasFactory
    0.79
    WriteTagHelper
    0.77
     oprot
    0.75
    ConstraintMaker
    0.72
    RegressionTest
    0.71
    IBarButtonItem
    0.71
    elemField
    0.71
     TextInputType
    0.69
    хьтан
    0.68
    Activations Density 0.247%

    No Known Activations