© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3628
    Prev
    Next
    INDEX
    Explanations

    travel

    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
    InvalidProtocol
    -0.96
    новништво
    -0.82
    ChildScrollView
    -0.82
    RenderAtEndOf
    -0.77
    ArgsConstructor
    -0.76
     متعلقه
    -0.75
     createState
    -0.75
     esternos
    -0.73
    Décès
    -0.71
     nahilalakip
    -0.70
    POSITIVE LOGITS
     or
    0.95
     this
    0.60
     like
    0.59
     или
    0.59
     you
    0.54
    或
    0.54
     eller
    0.53
    或者
    0.53
     atau
    0.52
     that
    0.50
    Activations Density 0.001%

    No Known Activations