© 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. 4-CLT-HP
    7. 4530
    Prev
    Next
    INDEX
    Explanations

    software and data

    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
    SBATCH
    -0.71
     riduzione
    -0.58
     mulighed
    -0.58
     strøm
    -0.57
     känna
    -0.56
    afficheront
    -0.56
     présidenti
    -0.55
    ConstraintMaker
    -0.55
     äta
    -0.55
     épaules
    -0.55
    POSITIVE LOGITS
    QObject
    0.57
    AccessorTable
    0.56
     fruits
    0.56
     meat
    0.55
     spoiled
    0.54
     nuts
    0.54
     chilled
    0.52
    Serializable
    0.52
     ArrayAdapter
    0.51
     fruit
    0.51
    Activations Density 0.002%

    No Known Activations