© 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. 94071
    Prev
    Next
    INDEX
    Explanations

    at

    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
    clearTimeout
    -0.49
     sn
    -0.39
    iest
    -0.37
     first
    -0.37
     infiltration
    -0.36
    rittura
    -0.36
     portato
    -0.36
    iglio
    -0.35
     sucedido
    -0.35
     betrayal
    -0.35
    POSITIVE LOGITS
    featureID
    1.07
    contentLoaded
    1.00
    -------------</
    0.82
     للاسماء
    0.77
    DeleteBehavior
    0.75
    EndGlobalSection
    0.74
    SourceChecksum
    0.74
    mybatisplus
    0.73
    MemoryWarning
    0.73
    alyptus
    0.73
    Activations Density 0.001%

    No Known Activations