© 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. 4-CLT-HP
    7. 3161
    Prev
    Next
    INDEX
    Explanations

    prepositions/punctuation

    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
    RegistryLite
    -0.79
    oa̍t
    -0.77
     Meksiku
    -0.74
     ویکی‌پدیا
    -0.74
    awtextra
    -0.73
    انيف
    -0.73
     beginnetje
    -0.73
    :✨
    -0.73
     مشين
    -0.70
    Datuak
    -0.69
    POSITIVE LOGITS
    bbene
    0.48
     jouets
    0.41
     supuestamente
    0.40
     takk
    0.39
    primento
    0.39
     creciendo
    0.39
     néz
    0.38
     nucléaire
    0.38
     navires
    0.38
    ientí
    0.38
    Activations Density 0.042%

    No Known Activations