© 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. 93995
    Prev
    Next
    INDEX
    Explanations

    categories of things

    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
     sometimes
    -0.77
    tagext
    -0.66
     EconPapers
    -0.64
    principalColumn
    -0.64
     soms
    -0.62
    )"),
    -0.60
    UnusedPrivate
    -0.58
     kadang
    -0.58
    ContentLoaded
    -0.57
     parfois
    -0.56
    POSITIVE LOGITS
     giapp
    0.48
     rezer
    0.47
     or
    0.47
     Offisielt
    0.46
    Geplaatst
    0.46
    或者
    0.46
     vayas
    0.46
    Vea
    0.45
     или
    0.45
     statunit
    0.45
    Activations Density 0.001%

    No Known Activations