© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4280
    Prev
    Next
    INDEX
    Explanations

    Puerto Rico

    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
    RegressionTest
    -0.47
    ClientSize
    -0.44
    слова
    -0.43
    ouver
    -0.43
     adjudged
    -0.41
    ɜ
    -0.41
     Савезне
    -0.40
     reward
    -0.38
     awards
    -0.38
    小编
    -0.38
    POSITIVE LOGITS
    expandindo
    0.97
     AssemblyCulture
    0.91
     виправивши
    0.77
     NSCoder
    0.75
     Pingback
    0.74
    VersionUID
    0.66
     TextAppearance
    0.61
     Normdatei
    0.61
     BoxFit
    0.60
     HttpNotFound
    0.60
    Activations Density 0.001%

    No Known Activations