© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1954
    Prev
    Next
    INDEX
    Explanations

    forcefully

    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
    mares
    -0.76
     unquestionably
    -0.59
    istically
    -0.57
    heartedly
    -0.49
     effectivement
    -0.49
     purported
    -0.47
     forcibly
    -0.46
     kud
    -0.46
     Meksiku
    -0.46
    CodeAnalysis
    -0.46
    POSITIVE LOGITS
     estekak
    0.81
     متعلقه
    0.74
     الرياضيه
    0.62
    multirow
    0.59
     simpler
    0.57
     diametro
    0.57
     istället
    0.56
    ніципалі
    0.56
     continuant
    0.56
     Efq
    0.55
    Activations Density 1.182%

    No Known Activations