© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95775
    Prev
    Next
    INDEX
    Explanations

    OutputType

    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
    Negative Logits
    下载附件
    -0.63
    Datuak
    -0.60
    icoot
    -0.59
     Normdatei
    -0.58
     laude
    -0.57
    :+:
    -0.56
     <<<<<<<<<<<<<<
    -0.54
    onOptions
    -0.54
     ролях
    -0.54
    
    -0.54
    POSITIVE LOGITS
    reportWebVitals
    0.59
    ,$_
    0.57
    })->
    0.57
     transférez
    0.54
    limsy
    0.53
    })()
    0.51
     LoggerFactory
    0.51
    WindowConstants
    0.51
    felde
    0.50
    */)
    0.49
    Activations Density 1.774%

    No Known Activations