© 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. 5-CLT-HP
    4. 12
    Prev
    Next
    INDEX
    Explanations

    identity

    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
     fácilmente
    -0.56
    Portale
    -0.56
    fonds
    -0.55
    "}")
    -0.54
     visuales
    -0.54
     líquido
    -0.54
     GenerationType
    -0.53
    人民共和国
    -0.52
     visibilité
    -0.52
     ilmu
    -0.52
    POSITIVE LOGITS
    ArgsConstructor
    0.65
    Condol
    0.61
     <>",
    0.53
    EndProject
    0.52
    ContentAlignment
    0.50
    ardless
    0.48
    ServletException
    0.47
     BorderRadius
    0.47
    Erreferentziak
    0.46
     Ayuntamiento
    0.46
    Activations Density 0.002%

    No Known Activations