© 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. 94778
    Prev
    Next
    INDEX
    Explanations

    bre

    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
     fast
    -1.01
     g
    -0.97
    __':
    -0.75
    IntoConstraints
    -0.67
     BoxFit
    -0.60
     AssemblyTitle
    -0.59
    IsContent
    -0.59
    adaptiveStyles
    -0.59
    </thead>
    -0.58
     gross
    -0.58
    POSITIVE LOGITS
     mijne
    0.93
     zijne
    0.87
     enfans
    0.83
     argint
    0.82
     barbati
    0.79
     Theſe
    0.77
     umane
    0.76
     feroit
    0.76
     giapp
    0.75
     crochê
    0.74
    Activations Density 0.141%

    No Known Activations