© 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. 4-CLT-HP
    7. 2438
    Prev
    Next
    INDEX
    Explanations

    similar

    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
     nettement
    -0.68
     battre
    -0.68
     supérieurs
    -0.68
     devenus
    -0.66
     réguli
    -0.65
     sauver
    -0.65
     refusé
    -0.65
     tenté
    -0.64
     mourir
    -0.63
     يتيمه
    -0.62
    POSITIVE LOGITS
     size
    0.95
     sizes
    0.84
     sized
    0.82
     amounts
    0.79
     magnitude
    0.73
     levels
    0.71
     lengths
    0.69
     proportions
    0.69
     quantities
    0.68
    size
    0.66
    Activations Density 0.004%

    No Known Activations