© 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. 1-CLT-HP
    7. 773
    Prev
    Next
    INDEX
    Explanations

    Signals, level

    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
     kaarangay
    -0.71
    setVerticalGroup
    -0.68
    UnusedPrivate
    -0.67
    tagHelperRunner
    -0.65
     utafitiHapana
    -0.65
    LookAnd
    -0.63
    NamedQueries
    -0.52
    SharedDtor
    -0.50
     الحره
    -0.50
    migrationBuilder
    -0.50
    POSITIVE LOGITS
     Partagez
    0.62
    prepareStatement
    0.57
    Xna
    0.53
    epam
    0.53
     pymysql
    0.52
     balanceOf
    0.52
     Denison
    0.52
     Deere
    0.50
    Autowired
    0.50
     JpaRepository
    0.50
    Activations Density 0.054%

    No Known Activations