© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45639
    Prev
    Next
    INDEX
    Explanations

    typescript and academic writing

    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
    tate
    -1.12
     الدولى
    -0.64
    ěstí
    -0.63
     Toibin
    -0.60
     skrive
    -0.60
     InputDecoration
    -0.59
     vård
    -0.57
    wój
    -0.57
     متعلقه
    -0.56
     séjours
    -0.56
    POSITIVE LOGITS
    Personensuche
    0.57
    AddHtmlAttribute
    0.56
    Autoritní
    0.55
    RectangleBorder
    0.55
    +:+
    0.53
    caster
    0.51
    UnusedPrivate
    0.50
     mar
    0.50
    casted
    0.47
    raten
    0.45
    Activations Density 0.082%

    No Known Activations