© 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. 20-CLT-HP
    7. 75925
    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
    +#+#
    -0.89
    __':
    -0.65
    __':
    -0.62
    fjspx
    -0.60
    ScopeManager
    -0.60
    HasForeignKey
    -0.59
     Havel
    -0.57
     headache
    -0.56
    WebServlet
    -0.56
     GenerationType
    -0.56
    POSITIVE LOGITS
    Koordinaten
    0.47
     Lokales
    0.45
     Мексичка
    0.43
     foot
    0.41
    vdash
    0.41
    зулта
    0.40
    pement
    0.40
    勉
    0.40
     spé
    0.40
    libft
    0.39
    Activations Density 0.000%

    No Known Activations