© 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. 5-CLT-HP
    7. 535
    Prev
    Next
    INDEX
    Explanations

    litter

    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
     Seeder
    -0.81
    ंदीखरीदारी
    -0.72
    Personensuche
    -0.72
    WithIOException
    -0.72
    WebElementEntity
    -0.69
    fillType
    -0.63
     disambiguazione
    -0.60
    writeFieldEnd
    -0.58
     nakalista
    -0.58
    AndEndTag
    -0.57
    POSITIVE LOGITS
     invece
    0.54
    gri
    0.51
     exception
    0.51
    CHOICES
    0.49
     kecelakaan
    0.49
    ẫy
    0.48
    ESTAMP
    0.48
    DataPropertyName
    0.47
    STRU
    0.47
     notwithstanding
    0.46
    Activations Density 0.032%

    No Known Activations