© 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. 1-CLT-HP
    7. 292
    Prev
    Next
    INDEX
    Explanations

    visible

    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
     iVar
    -0.71
    principalColumn
    -0.69
    ьаж
    -0.64
    #
    -0.60
     uLocal
    -0.58
     kasarigan
    -0.56
    shed
    -0.56
    IsInitialized
    -0.55
    +:+
    -0.52
    /*
    -0.52
    POSITIVE LOGITS
    EnableWeb
    0.62
    互联网档案馆
    0.52
     sitesinde
    0.50
    ooga
    0.48
     dirig
    0.48
    izing
    0.48
    醐
    0.48
    []
    0.48
    ising
    0.47
    ❸
    0.47
    Activations Density 0.034%

    No Known Activations