© 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. 38557
    Prev
    Next
    INDEX
    Explanations

    competition and success

    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
     win
    -1.22
     assist
    -0.87
     steal
    -0.84
    win
    -0.79
     Win
    -0.69
    Win
    -0.64
    steal
    -0.62
    lossians
    -0.60
    assist
    -0.59
    longer
    -0.58
    POSITIVE LOGITS
     figliu
    0.66
     itſelf
    0.63
     rádio
    0.62
     indipendente
    0.62
     cucchia
    0.60
     judiciales
    0.60
     compét
    0.60
     nemico
    0.59
    memoized
    0.59
     originaux
    0.59
    Activations Density 0.037%

    No Known Activations