© 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. 94107
    Prev
    Next
    INDEX
    Explanations

    Research papers

    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
    <eos>
    -0.34
     COVID
    -0.30
    ↵↵
    -0.25
    ль
    -0.25
    ans
    -0.24
    セ
    -0.24
    新冠
    -0.24
     im
    -0.23
     ‘
    -0.23
     hingga
    -0.23
    POSITIVE LOGITS
    webElementXpaths
    1.06
    LookAnd
    1.05
    GEBURTSDATUM
    1.05
     beginnetje
    1.01
    PerformLayout
    1.00
     الحره
    0.99
     חיצוניים
    0.97
    TagMode
    0.96
     AppCompatTheme
    0.96
    MigrationBuilder
    0.95
    Activations Density 0.041%

    No Known Activations