© 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
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 4477
    Prev
    Next
    INDEX
    Explanations

    code and filenames

    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
     turning
    -0.56
     counting
    -0.52
    >>();
    -0.49
    "}")
    -0.48
     fore
    -0.48
     remaining
    -0.47
    >>()
    -0.47
     count
    -0.46
     собой
    -0.45
    เหลือ
    -0.45
    POSITIVE LOGITS
    contentLoaded
    0.71
     AssemblyTitle
    0.68
    esModule
    0.62
     juridiques
    0.60
    AddHtmlAttribute
    0.60
     voulait
    0.59
     étanche
    0.59
     jurí
    0.59
     mourut
    0.58
    textTheme
    0.58
    Activations Density 0.003%

    No Known Activations