© 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. 90983
    Prev
    Next
    INDEX
    Explanations

    article snippets/titles

    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
    llbracket
    -0.44
    translateX
    -0.43
    efeated
    -0.42
    ibilità
    -0.41
     tỉ
    -0.40
    객
    -0.40
    ImageField
    -0.39
    twin
    -0.39
    rzej
    -0.39
    ÍST
    -0.39
    POSITIVE LOGITS
     تضيفلها
    0.92
     AssemblyProduct
    0.77
    BeginContext
    0.72
    numerusform
    0.71
    PerformLayout
    0.69
    MigrationBuilder
    0.68
    AddTagHelper
    0.68
     distanciation
    0.68
    SerializedName
    0.67
    BufferException
    0.66
    Activations Density 1.628%

    No Known Activations