© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96208
    Prev
    Next
    INDEX
    Explanations

    who

    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
     متعلقه
    -0.43
     }_{
    -0.41
     sobretudo
    -0.40
     those
    -0.40
     indispensables
    -0.38
     Hat
    -0.37
     lyder
    -0.37
    BeginInit
    -0.37
    akah
    -0.36
    そして
    -0.36
    POSITIVE LOGITS
    клопе
    0.69
    AddTagHelper
    0.64
     désolés
    0.62
    Namara
    0.60
     understood
    0.59
    uxxxx
    0.59
    complexContent
    0.58
     understand
    0.58
     see
    0.58
     dared
    0.57
    Activations Density 0.002%

    No Known Activations