© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92028
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     oreilles
    -0.58
     Juifs
    -0.52
     mêmes
    -0.52
    </thead>
    -0.51
     lèvres
    -0.51
    San
    -0.50
     egyik
    -0.50
     épaules
    -0.50
    amentul
    -0.50
     réfugiés
    -0.49
    POSITIVE LOGITS
    StoryboardSegue
    0.82
    adaptiveStyles
    0.73
    хьтан
    0.73
    aarrggbb
    0.66
     referenties
    0.65
    ised
    0.65
    Vidite
    0.63
    ity
    0.63
    ize
    0.63
    ities
    0.61
    Activations Density 0.018%

    No Known Activations