© 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. 0-CLT-HP
    7. 42100
    Prev
    Next
    INDEX
    Explanations

    ordeal

    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
    werve
    -0.68
     ordeal
    -0.62
     mug
    -0.58
    puter
    -0.42
     survives
    -0.40
    gues
    -0.39
    tidase
    -0.34
    igram
    -0.34
     fals
    -0.33
     stay
    -0.33
    POSITIVE LOGITS
    expandindo
    1.03
    Билгалдахарш
    1.02
    +#+
    1.01
     initComponents
    0.98
     propOrder
    0.97
     nahilalakip
    0.94
    OGND
    0.93
    出版年
    0.93
     jScrollPane
    0.92
     defaultstate
    0.91
    Activations Density 1.526%

    No Known Activations