Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 240
    Prev
    Next
    INDEX
    Explanations

    not

    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
    i
    -0.75
    did
    -0.68
    a
    -0.68
    do
    -0.66
    ex
    -0.65
    had
    -0.62
    eg
    -0.58
    ed
    -0.56
    say
    -0.53
    c
    -0.53
    POSITIVE LOGITS
     للاسماء
    1.25
    ViewFeatures
    1.14
     ExecuteAsync
    1.12
    SourceChecksum
    1.11
    IUrlHelper
    1.11
     Мексичка
    1.09
    IndentedString
    1.09
    tvguidetime
    1.06
    :✨
    1.05
    WithIOException
    1.05
    Activations Density 0.029%

    No Known Activations