© 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. 4-CLT-HP
    7. 4357
    Prev
    Next
    INDEX
    Explanations

    software development

    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
     مشين
    -0.57
     ویکی‌پدی
    -0.57
     Roskov
    -0.57
    tonsoft
    -0.56
    wanza
    -0.55
    IUrlHelper
    -0.54
    ánt
    -0.54
     Lamont
    -0.54
    bust
    -0.54
    razione
    -0.54
    POSITIVE LOGITS
     Piles
    0.59
     DialogInterface
    0.51
    AndEndTag
    0.48
    phile
    0.47
    TextInputLayout
    0.46
    PreExecute
    0.45
    ])));
    0.42
    ArrowToggle
    0.41
    kfree
    0.41
     calculées
    0.41
    Activations Density 0.002%

    No Known Activations