Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73912
    Prev
    Next
    INDEX
    Explanations

    Code context

    np_max-act-logits · 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
    клопе
    -0.81
    Aholisi
    -0.65
    出版年
    -0.65
    featureID
    -0.57
    making
    -0.56
     replacing
    -0.55
    IORS
    -0.54
     насељу
    -0.54
    elect
    -0.54
    igate
    -0.54
    POSITIVE LOGITS
    tvguidetime
    0.53
    CppMethod
    0.47
     inters
    0.45
     inder
    0.44
    ༘
    0.44
     تضيفلها
    0.43
     NavController
    0.42
     reger
    0.41
     adven
    0.41
     chng
    0.41
    Activations Density 0.002%

    No Known Activations