© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 95049
    Prev
    Next
    INDEX
    Explanations

    break

    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
     break
    -1.27
     breaking
    -1.08
    break
    -1.05
     broken
    -0.99
     Broken
    -0.94
     Breaking
    -0.90
     broke
    -0.89
     Break
    -0.87
    breaking
    -0.85
    Breaking
    -0.82
    POSITIVE LOGITS
    awtextra
    0.62
    memoized
    0.61
    tonode
    0.60
    StructEnd
    0.59
    pozdrawiam
    0.59
    Geplaatst
    0.51
    setVerticalGroup
    0.51
     سكانية
    0.49
    Équipe
    0.48
    VIAF
    0.48
    Activations Density 0.027%

    No Known Activations