Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4281
    Prev
    Next
    INDEX
    Explanations

    to be

    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
     in
    -0.57
     making
    -0.55
     doing
    -0.54
     on
    -0.51
     válto
    -0.49
     getting
    -0.47
     ennek
    -0.47
     sitting
    -0.45
     everywhere
    -0.45
     bouncing
    -0.44
    POSITIVE LOGITS
    ContentAsync
    0.64
    دانشنامهٔ
    0.63
    SpringBootTest
    0.59
     وتسجيلات
    0.56
    DockStyle
    0.55
    styleUrls
    0.55
     NSString
    0.55
    cerely
    0.52
    IContainer
    0.52
    MigrationBuilder
    0.52
    Activations Density 0.005%

    No Known Activations