© 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. 20-CLT-HP
    7. 76347
    Prev
    Next
    INDEX
    Explanations

    foreign words

    np_max-act-logits · 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
    ViewChild
    -0.56
     Halls
    -0.46
    BindView
    -0.45
     فريبيس
    -0.45
    habits
    -0.44
     Walls
    -0.42
     Rooms
    -0.42
    hObject
    -0.42
     Tanks
    -0.42
     Plates
    -0.41
    POSITIVE LOGITS
     autorytatywna
    0.63
     étrangères
    0.63
     internationaux
    0.61
     médicaux
    0.60
     âgées
    0.59
     decorados
    0.57
     fermés
    0.57
     africains
    0.57
    cover
    0.56
     suivants
    0.56
    Activations Density 0.010%

    No Known Activations