© 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. 4-CLT-HP
    7. 3497
    Prev
    Next
    INDEX
    Explanations

    thick

    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
    INA
    -0.55
    ipedia
    -0.50
    sef
    -0.50
     r
    -0.47
     transférez
    -0.47
    ByExample
    -0.46
     wonderful
    -0.46
     retiring
    -0.46
    SpringBootTest
    -0.46
    garet
    -0.45
    POSITIVE LOGITS
    Tikang
    0.69
    TemporalType
    0.60
     EClass
    0.55
     endwhile
    0.55
     MainAxisSize
    0.54
    日閲覧
    0.53
     geweest
    0.53
     []:
    0.53
     estekak
    0.51
    DeleteBehavior
    0.50
    Activations Density 0.003%

    No Known Activations