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. 0-CLT-HP
    4. 38
    Prev
    Next
    INDEX
    Explanations

    symmetry

    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
     perspective
    -1.04
     context
    -0.95
    perspective
    -0.94
     Perspective
    -0.91
     purpoſe
    -0.90
     perspek
    -0.89
    symmetry
    -0.88
     Emergence
    -0.88
     Context
    -0.87
     prospet
    -0.82
    POSITIVE LOGITS
    ,
    0.59
     and
    0.58
    Климат
    0.54
    djangoproject
    0.54
     also
    0.52
    ↵↵
    0.51
     in
    0.51
    :
    0.50
     for
    0.50
    .
    0.48
    Activations Density 0.050%

    No Known Activations