© 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. 0-CLT-HP
    7. 1635
    Prev
    Next
    INDEX
    Explanations

    Roman numerals

    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
    nice
    -0.41
     to
    -0.41
    heating
    -0.40
    withOpacity
    -0.40
    worthy
    -0.40
    plots
    -0.39
    一波
    -0.39
    ाय
    -0.39
    tells
    -0.38
    weights
    -0.38
    POSITIVE LOGITS
    <bos>
    0.83
    SourceChecksum
    0.83
    LookAnd
    0.82
    AddTagHelper
    0.81
     gynhyrchwyd
    0.76
     nahilalakip
    0.75
    Geplaatst
    0.74
    InjectAttribute
    0.74
    webElementXpaths
    0.74
    DockStyle
    0.73
    Activations Density 0.202%

    No Known Activations