© 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. 4-CLT-HP
    7. 3261
    Prev
    Next
    INDEX
    Explanations

    The

    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
     WaitForSeconds
    -0.84
    IUrlHelper
    -0.82
     snippetHide
    -0.76
    StoryboardSegue
    -0.75
    WithIOException
    -0.75
    IsContent
    -0.74
     ElementRef
    -0.73
    Portail
    -0.72
    principalTable
    -0.72
     ويكيپيديا
    -0.72
    POSITIVE LOGITS
    /*++
    0.38
     étions
    0.37
     exclusivas
    0.37
    noo
    0.36
     ("
    0.36
    ่อน
    0.36
     fidèles
    0.36
    لاً
    0.36
    ورد
    0.36
    ViewFeatures
    0.35
    Activations Density 0.063%

    No Known Activations