© 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. 4421
    Prev
    Next
    INDEX
    Explanations

    coming

    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
    oplayer
    -0.54
     Résultat
    -0.53
    Datuak
    -0.53
    ROIT
    -0.52
    󠁿
    -0.51
     Bully
    -0.50
    ργασ
    -0.49
    脚注の使い方
    -0.49
     DPM
    -0.49
     DIES
    -0.48
    POSITIVE LOGITS
     transfieras
    0.59
     storm
    0.59
     Савезне
    0.58
    :✨
    0.56
     initComponents
    0.56
    InstrumentedTest
    0.54
    soon
    0.51
     storms
    0.50
    AnchorTagHelper
    0.49
    ColumnHeaders
    0.49
    Activations Density 0.001%

    No Known Activations