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. 5-CLT-HP
    4. 95569
    Prev
    Next
    INDEX
    Explanations

    of/the

    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
    Which
    -0.54
    quels
    -0.54
     hvilket
    -0.53
     calendriers
    -0.51
     laquelle
    -0.50
     opportunità
    -0.49
    wanych
    -0.49
    Lähteet
    -0.49
     lesquels
    -0.49
     lequel
    -0.49
    POSITIVE LOGITS
     oprot
    0.73
     that
    0.65
    even
    0.64
     sice
    0.60
     even
    0.59
    XmlType
    0.55
    tze
    0.54
    nloa
    0.53
    STATUS
    0.52
     accordingly
    0.52
    Activations Density 0.006%

    No Known Activations