© 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. 0-CLT-HP
    7. 90989
    Prev
    Next
    INDEX
    Explanations

    discovery

    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
     discovery
    -2.47
    discovery
    -2.02
     Discovery
    -1.88
    Discovery
    -1.86
     discovered
    -1.75
     découverte
    -1.64
     descubrimiento
    -1.64
     discovering
    -1.61
     discoveries
    -1.61
     discover
    -1.59
    POSITIVE LOGITS
    ,
    0.62
    <bos>
    0.59
     in
    0.55
     es
    0.55
     o
    0.54
     as
    0.53
    .
    0.53
    InjectAttribute
    0.53
     to
    0.51
     by
    0.51
    Activations Density 0.315%

    No Known Activations