© 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. 0-CLT-HP
    7. 95040
    Prev
    Next
    INDEX
    Explanations

    okay

    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
    wet
    -1.05
     wet
    -1.02
     Wet
    -0.96
    Wet
    -0.93
     dries
    -0.93
    dry
    -0.82
     drying
    -0.81
     dried
    -0.78
    WET
    -0.77
    drying
    -0.75
    POSITIVE LOGITS
    StoryboardSegue
    0.57
     مواليد
    0.57
     sandwiches
    0.54
    inafter
    0.53
    ened
    0.52
     sandwich
    0.50
    script
    0.49
     armb
    0.48
    География
    0.47
    engertian
    0.47
    Activations Density 0.073%

    No Known Activations