© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4295
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    WithIOException
    -0.73
    InjectAttribute
    -0.72
    clusal
    -0.66
    DoubleQuotes
    -0.65
    MergeFrom
    -0.65
    rungsseite
    -0.65
    __":
    -0.61
     Masonry
    -0.60
    ValueStyle
    -0.59
    MigrationBuilder
    -0.59
    POSITIVE LOGITS
    lanması
    0.51
     meilleures
    0.50
     devriez
    0.45
     rosse
    0.45
     makinesi
    0.44
     religieuse
    0.43
     canadienne
    0.42
     générations
    0.42
     appunto
    0.41
     chrétien
    0.41
    Activations Density 0.006%

    No Known Activations