© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92064
    Prev
    Next
    INDEX
    Explanations

    Facebook

    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
     ...
    -0.32
     «
    -0.31
      
    -0.29
     p
    -0.28
     And
    -0.28
     AND
    -0.28
     (
    -0.27
     `
    -0.27
    ...
    -0.26
    而言
    -0.26
    POSITIVE LOGITS
     ſeveral
    1.09
    }.
    0.97
     myſelf
    0.96
     Efq
    0.96
     ſmall
    0.96
     houſe
    0.94
    !")
    0.91
     Monfieur
    0.91
     greateſt
    0.90
     Majefty
    0.90
    Activations Density 0.006%

    No Known Activations