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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73450
    Prev
    Next
    INDEX
    Explanations

    detects source code

    np_max-act-logits · 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
    orteur
    -0.59
    .*")]
    -0.59
     EClass
    -0.56
    További
    -0.53
     ivelany
    -0.49
    壤
    -0.48
    jupiter
    -0.47
    __);
    -0.47
     assurent
    -0.47
    >*/
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.60
     XMLHttpRequest
    0.59
    ModelAdmin
    0.54
    +#+
    0.52
    ymce
    0.49
    dersfield
    0.48
    ########.
    0.48
     Bunk
    0.47
    ientôt
    0.47
     GenerationType
    0.47
    Activations Density 0.000%

    No Known Activations