© 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. 1-CLT-HP
    7. 12165
    Prev
    Next
    INDEX
    Explanations

    some

    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
     surla
    -0.48
     of
    -0.47
     csomag
    -0.47
    不如
    -0.47
    GeneratedCode
    -0.45
    espère
    -0.43
    ariah
    -0.43
    aurais
    -0.42
     noDo
    -0.42
    φέρει
    -0.42
    POSITIVE LOGITS
    migrationBuilder
    0.69
     sharks
    0.59
    ⓧ
    0.57
     ducks
    0.57
    ducks
    0.53
    Ducks
    0.53
     turtles
    0.52
     turtle
    0.52
     onCancelled
    0.52
     dolphins
    0.51
    Activations Density 0.011%

    No Known Activations