© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1098
    Prev
    Next
    INDEX
    Explanations

    important

    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
     Majefty
    -0.84
     greateſt
    -0.80
     enfans
    -0.77
    ſelf
    -0.73
     tramonto
    -0.72
     ſtate
    -0.70
     Diſ
    -0.68
     beginnetje
    -0.68
     fufficient
    -0.67
     touristes
    -0.67
    POSITIVE LOGITS
     betweenstory
    0.59
     points
    0.59
     question
    0.58
     purposes
    0.57
     idea
    0.56
     functions
    0.52
     areas
    0.50
    LabelTagHelper
    0.50
     questions
    0.49
     task
    0.49
    Activations Density 0.008%

    No Known Activations