© 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. 94077
    Prev
    Next
    INDEX
    Explanations

    technical/research text

    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
     ostavi
    -0.76
     виправивши
    -0.75
    >{@
    -0.74
    发表于
    -0.73
     AssemblyCulture
    -0.73
     INTERESAR
    -0.70
     tué
    -0.69
     CreateTagHelper
    -0.66
     autorytatywna
    -0.65
     disambiguazione
    -0.64
    POSITIVE LOGITS
    PositiveButton
    0.54
    apunov
    0.52
     attractive
    0.49
     counters
    0.48
     counter
    0.48
    不上
    0.48
     SearchView
    0.47
    odynamic
    0.47
    CastException
    0.46
     la
    0.46
    Activations Density 0.014%

    No Known Activations