© 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. 97979
    Prev
    Next
    INDEX
    Explanations

    geographic locations

    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
    StructEnd
    -0.73
    SourceChecksum
    -0.60
     surla
    -0.56
    transQ
    -0.55
    cipar
    -0.50
    SharedCtor
    -0.49
    aarrggbb
    -0.48
     متعلقه
    -0.47
    autique
    -0.46
     Audiodateien
    -0.46
    POSITIVE LOGITS
    autoreleasepool
    0.60
    OptionsMenu
    0.59
     defStyle
    0.58
     Scheiben
    0.58
    tagHelper
    0.58
    quias
    0.54
     BoxFit
    0.54
     onOptions
    0.54
    ΩΝ
    0.52
    onAttach
    0.52
    Activations Density 0.003%

    No Known Activations