© 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. 1-CLT-HP
    7. 46228
    Prev
    Next
    INDEX
    Explanations

    famous

    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
     Famous
    -0.84
    Famous
    -0.80
     famous
    -0.80
    famous
    -0.77
     célèbres
    -0.73
     endforeach
    -0.67
     famosas
    -0.65
     fumée
    -0.65
    textTheme
    -0.63
     famosos
    -0.63
    POSITIVE LOGITS
    繁
    0.52
    tonsoft
    0.47
    tish
    0.45
    meture
    0.45
     weg
    0.44
    ourable
    0.43
     substance
    0.43
     programme
    0.43
     Touchable
    0.43
     resident
    0.42
    Activations Density 0.006%

    No Known Activations