© 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. 43622
    Prev
    Next
    INDEX
    Explanations

    aggregate

    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
     aggregate
    -2.00
     Aggregate
    -1.61
    aggregate
    -1.52
    Aggregate
    -1.48
     aggregates
    -1.39
     cumulative
    -1.30
     aggregated
    -1.23
     Cumulative
    -1.12
     aggregating
    -1.10
     Aggreg
    -1.07
    POSITIVE LOGITS
    دانشنامهٔ
    0.56
     newBuilder
    0.54
     calendriers
    0.50
    VIAF
    0.49
     pym
    0.49
     Differ
    0.48
    衛門
    0.48
    Quoted
    0.47
     BaseController
    0.47
    عل
    0.46
    Activations Density 0.248%

    No Known Activations