© 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. 40137
    Prev
    Next
    INDEX
    Explanations

    /

    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
    :✨
    -0.87
    sizeCache
    -0.81
    Personendaten
    -0.80
     AssemblyCulture
    -0.75
    NameInMap
    -0.67
     autorytatywna
    -0.66
    /******/
    -0.63
     disambiguazione
    -0.58
    исленность
    -0.58
    EndContext
    -0.57
    POSITIVE LOGITS
     varandra
    0.54
     būs
    0.52
     Chriftian
    0.47
     användas
    0.47
     obstante
    0.47
     modalités
    0.47
    DTD
    0.47
     iſt
    0.46
    ⤒
    0.46
     $_"
    0.45
    Activations Density 0.251%

    No Known Activations