© 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. 20-CLT-HP
    7. 73133
    Prev
    Next
    INDEX
    Explanations

    WiFi access points

    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
    complexContent
    -0.80
    TagHelper
    -0.75
    setVerticalGroup
    -0.69
     "..\..\..\
    -0.68
    CloseOperation
    -0.68
    MigrationBuilder
    -0.66
    AutoField
    -0.66
    fjspx
    -0.65
    ScopeManager
    -0.61
    ctomy
    -0.61
    POSITIVE LOGITS
     AP
    0.66
     Access
    0.64
     access
    0.60
     hotspots
    0.60
     SS
    0.56
     hotspot
    0.56
     hot
    0.55
     Hot
    0.54
    Access
    0.53
    hot
    0.53
    Activations Density 0.045%

    No Known Activations