© 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. 0-CLT-HP
    7. 38282
    Prev
    Next
    INDEX
    Explanations

    successful, subgroup

    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
     الحره
    -0.74
    Restricted
    -0.72
     restricted
    -0.68
     CURLOPT
    -0.67
    restricted
    -0.66
     Restricted
    -0.65
    новништво
    -0.62
    Viewed
    -0.59
    ThroughAttribute
    -0.59
     locomo
    -0.56
    POSITIVE LOGITS
    complexContent
    0.63
    setCellValue
    0.61
    WebElementEntity
    0.52
    SharedDtor
    0.52
     nakalista
    0.51
     Pire
    0.49
     Chron
    0.47
    ')}}
    0.47
    .*")]
    0.47
    èdia
    0.47
    Activations Density 1.482%

    No Known Activations