© 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. 0-CLT-HP
    7. 2001
    Prev
    Next
    INDEX
    Explanations

    Thereafter

    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
    ouan
    -1.04
    vera
    -0.73
    uct
    -0.57
     it
    -0.55
     to
    -0.54
     s
    -0.51
    .
    -0.51
     st
    -0.48
     then
    -0.47
     jour
    -0.46
    POSITIVE LOGITS
    QMetaType
    1.03
     myſelf
    1.03
     Majefty
    1.01
     Theſe
    1.00
    AndEndTag
    0.97
    ſelf
    0.95
    ſelves
    0.93
    ViewFeatures
    0.93
     utafitiHapana
    0.93
     pleaſure
    0.91
    Activations Density 0.844%

    No Known Activations