© 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. 5-CLT-HP
    7. 839
    Prev
    Next
    INDEX
    Explanations

    prove

    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
     يتيمه
    -0.65
    出版年
    -0.57
    opher
    -0.54
    <bos>
    -0.53
    OrNull
    -0.52
     Ανακτήθηκε
    -0.52
    fontawesome
    -0.52
    etCode
    -0.50
     امريكا
    -0.49
    spesies
    -0.49
    POSITIVE LOGITS
     reluctant
    0.69
     estekak
    0.62
     unwilling
    0.59
     unprepared
    0.59
     defaultstate
    0.58
     فريبيس
    0.57
     willing
    0.56
     prone
    0.56
     vulnerable
    0.55
     competent
    0.55
    Activations Density 0.005%

    No Known Activations