© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1951
    Prev
    Next
    INDEX
    Explanations

    survey, collected

    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
    saraba
    -0.96
     propOrder
    -0.91
     HasFactory
    -0.88
     ainfi
    -0.85
    WebElementEntity
    -0.83
     ब्रेकडाउन
    -0.83
     ujednoznacz
    -0.80
    AddTagHelper
    -0.78
     plufieurs
    -0.78
    rungsseite
    -0.77
    POSITIVE LOGITS
    ↵↵
    0.63
    ’
    0.63
    ed
    0.63
    .
    0.58
    '
    0.58
     using
    0.52
     a
    0.51
     for
    0.51
     T
    0.51
     that
    0.51
    Activations Density 0.353%

    No Known Activations