© 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. 0-CLT-HP
    7. 1834
    Prev
    Next
    INDEX
    Explanations

    harsh conditions, dips

    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
     Harsh
    -0.82
     AspNetCore
    -0.77
    Personendaten
    -0.77
     stric
    -0.72
     Strict
    -0.71
    WithIOException
    -0.71
    aarrggbb
    -0.69
    Harsh
    -0.68
     estric
    -0.68
     оригіналу
    -0.63
    POSITIVE LOGITS
    ness
    1.01
    ening
    0.83
    stand
    0.75
    est
    0.70
    iness
    0.68
    ifying
    0.64
    ard
    0.63
    ener
    0.60
    eting
    0.59
    er
    0.59
    Activations Density 0.066%

    No Known Activations