© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45622
    Prev
    Next
    INDEX
    Explanations

    drop

    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
     drop
    -1.31
     dropped
    -1.25
    Drop
    -1.20
    drop
    -1.18
     drops
    -1.17
     Drop
    -1.16
     DROP
    -1.08
    dropped
    -1.06
     dropping
    -1.04
     Drops
    -1.00
    POSITIVE LOGITS
    ترنت
    0.54
    atcher
    0.48
    MigrationBuilder
    0.46
    PLING
    0.46
    complexContent
    0.45
    ant
    0.45
     Bourgoin
    0.45
     Mather
    0.44
    unsplash
    0.44
     bint
    0.43
    Activations Density 0.021%

    No Known Activations