© 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. 1-CLT-HP
    7. 10049
    Prev
    Next
    INDEX
    Explanations

    Spain

    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
    GraphicsUnit
    -0.86
     utafitiHapana
    -0.83
     nahilalakip
    -0.70
    (!__
    -0.69
     CreateTagHelper
    -0.67
    __(/*!
    -0.67
    TypedDataSet
    -0.66
    ItemBackground
    -0.65
    Collegamenti
    -0.64
     ExecuteAsync
    -0.64
    POSITIVE LOGITS
     disparu
    0.50
     décédé
    0.50
     abandonné
    0.47
     librement
    0.47
     pierdas
    0.47
    lasyon
    0.46
     desaparecido
    0.45
     marbre
    0.45
     fédéral
    0.44
    HostException
    0.44
    Activations Density 0.014%

    No Known Activations