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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39050
    Prev
    Next
    INDEX
    Explanations

    simply

    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
     simply
    -2.16
    Simply
    -2.11
    simply
    -2.11
     Simply
    -2.05
     semplicemente
    -1.68
     simplemente
    -1.64
     simplesmente
    -1.59
     simplement
    -1.54
     Simplemente
    -1.52
     einfach
    -1.35
    POSITIVE LOGITS
     the
    0.71
     a
    0.61
    SelectedIndex
    0.56
     “
    0.56
     rest
    0.54
     an
    0.53
     and
    0.52
     Shaffer
    0.51
     ‘
    0.50
     "
    0.50
    Activations Density 0.240%

    No Known Activations