© 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. 94031
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     estekak
    -0.56
    enumii
    -0.53
    HasAnnotation
    -0.50
     включает
    -0.49
     quarters
    -0.48
     ThemeData
    -0.48
    mtd
    -0.47
     Inclusion
    -0.47
    จึง
    -0.47
    wning
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.72
    oredCriteria
    0.62
    RetentionPolicy
    0.60
    ImageContext
    0.60
    resave
    0.60
    RegressionTest
    0.58
    LookAnd
    0.56
     sticking
    0.56
    setDo
    0.56
    CDCl
    0.53
    Activations Density 0.000%

    No Known Activations