© 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. 4298
    Prev
    Next
    INDEX
    Explanations

    min

    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
    onActivityResult
    -0.68
    httphttps
    -0.68
    viewDidLoad
    -0.62
     Waray
    -0.60
     Савезне
    -0.57
    GEBURTS
    -0.56
    }{*}{}
    -0.56
    WriteTagHelper
    -0.56
    -------------</
    -0.56
    tableFuture
    -0.54
    POSITIVE LOGITS
    <bos>
    0.78
    igare
    0.54
    vedať
    0.47
    ستان
    0.46
    Chham
    0.45
    プローチ
    0.45
     KGB
    0.44
     uporab
    0.44
     Wit
    0.43
     cut
    0.42
    Activations Density 0.002%

    No Known Activations