© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 924
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     myſelf
    -1.10
     AssemblyTitle
    -1.02
     Majefty
    -0.98
     Efq
    -0.97
     autorytatywna
    -0.96
     raiſ
    -0.96
     يتيمه
    -0.94
     himſelf
    -0.94
    ^(@)
    -0.94
    ſelf
    -0.93
    POSITIVE LOGITS
    </strong>
    0.43
     On
    0.38
    hs
    0.38
    ход
    0.37
     In
    0.36
    mstyle
    0.36
    </blockquote>
    0.36
     -
    0.35
    â
    0.35
    糊
    0.34
    Activations Density 0.003%

    No Known Activations