© 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. 97658
    Prev
    Next
    INDEX
    Explanations

    rather

    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
     of
    -0.52
    ’
    -0.35
    elin
    -0.35
    "
    -0.35
     talking
    -0.34
     or
    -0.34
     too
    -0.34
    őle
    -0.33
     them
    -0.33
     n
    -0.33
    POSITIVE LOGITS
     propOrder
    1.04
    +#+
    0.99
    twimg
    0.95
    RenderAtEndOf
    0.93
    InjectAttribute
    0.90
    tagHelperRunner
    0.88
     виправивши
    0.85
     للاسماء
    0.84
    WebVitals
    0.84
     EconPapers
    0.84
    Activations Density 0.001%

    No Known Activations