© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45576
    Prev
    Next
    INDEX
    Explanations

    us

    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
    IVEREF
    -0.86
     kaarangay
    -0.86
    OGND
    -0.85
     CreateTagHelper
    -0.79
     تضيفلها
    -0.79
     للاسماء
    -0.75
    DotNetBar
    -0.72
     <>",
    -0.72
     betweenstory
    -0.70
     متعلقه
    -0.69
    POSITIVE LOGITS
     MonoBehaviour
    0.47
    PreExecute
    0.47
    MigrationBuilder
    0.44
     contemporary
    0.41
     modernisation
    0.41
    SuccessListener
    0.40
     henkil
    0.40
    setContentView
    0.40
     modernization
    0.39
     declaratory
    0.38
    Activations Density 0.023%

    No Known Activations