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. 73415
    Prev
    Next
    INDEX
    Explanations

    Code and names

    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
    ftagPool
    -0.91
     '\\;'
    -0.75
    SuccessListener
    -0.69
    تفصیلات
    -0.69
    ValueStyle
    -0.68
    AddHtmlAttribute
    -0.67
    expandindo
    -0.66
    AnchorTagHelper
    -0.64
     termica
    -0.63
     referenties
    -0.63
    POSITIVE LOGITS
     wipe
    0.54
     wipes
    0.51
     rob
    0.48
     Wipe
    0.47
     equal
    0.46
     cost
    0.46
    vena
    0.44
     Swipe
    0.44
     shave
    0.41
     lop
    0.41
    Activations Density 0.001%

    No Known Activations