© 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. 384
    Prev
    Next
    INDEX
    Explanations

    discussion forum questions/answers

    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
    ValueStyle
    -0.62
    posedge
    -0.54
    EndGlobalSection
    -0.53
     autorytatywna
    -0.52
    Portail
    -0.47
    ponses
    -0.47
     Ben
    -0.46
     Roberts
    -0.45
    setAccessible
    -0.45
    Джерела
    -0.44
    POSITIVE LOGITS
    MLLoader
    0.60
     asiatique
    0.60
     pngtree
    0.58
    boîte
    0.57
     RSSSF
    0.56
     OFDb
    0.56
     gången
    0.56
    Raf
    0.56
     eenige
    0.55
     latine
    0.54
    Activations Density 0.000%

    No Known Activations