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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1284
    Prev
    Next
    INDEX
    Explanations

    Higher education institutions

    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
    ThroughAttribute
    -0.62
    RenderAtEndOf
    -0.62
    MemoryWarning
    -0.58
    InputBorder
    -0.58
    ViewById
    -0.57
    makeText
    -0.55
     виправивши
    -0.55
    strix
    -0.55
    bebasan
    -0.55
     volna
    -0.52
    POSITIVE LOGITS
     صوتيه
    0.76
     الدولى
    0.59
     متعلقه
    0.57
    Emilia
    0.56
     cherchés
    0.52
    lary
    0.50
    UnsafeEnabled
    0.50
    Susie
    0.50
     chi̍t
    0.49
    instancetype
    0.49
    Activations Density 0.062%

    No Known Activations