© 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. 72955
    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
    ReusableCell
    -0.63
    UnusedPrivate
    -0.63
     MainAxisSize
    -0.62
     ویکی‌پدیا
    -0.61
    tség
    -0.59
     propOrder
    -0.56
    IBar
    -0.56
    Geplaatst
    -0.55
    pul
    -0.55
     BorderRadius
    -0.52
    POSITIVE LOGITS
    قایناقلار
    0.49
    cerol
    0.45
    ={`
    0.45
    assertIn
    0.42
    Notifier
    0.42
    clable
    0.41
    Adel
    0.41
    forhold
    0.41
    Історія
    0.41
    reporting
    0.40
    Activations Density 0.000%

    No Known Activations