© 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. 92324
    Prev
    Next
    INDEX
    Explanations

    community

    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
    UrlResolution
    -0.63
    
    -0.63
    AsUp
    -0.62
     سكانية
    -0.55
    ArgsConstructor
    -0.53
    PreferredItem
    -0.51
    >{@
    -0.48
    السكان
    -0.48
     refineries
    -0.48
    ForRow
    -0.48
    POSITIVE LOGITS
     center
    0.79
     centre
    0.77
     events
    0.70
    center
    0.66
    centre
    0.65
     centers
    0.61
     centres
    0.59
     fair
    0.59
     event
    0.58
     Center
    0.57
    Activations Density 0.001%

    No Known Activations