© 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. 0-CLT-HP
    7. 91181
    Prev
    Next
    INDEX
    Explanations

    Abbreviations/shortened forms

    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
    SpringBootTest
    -0.77
     оригіналу
    -0.72
     transfieras
    -0.68
    XtraReports
    -0.64
    DrawerToggle
    -0.63
    ListItemIcon
    -0.63
     doubtnut
    -0.61
     cdti
    -0.60
     Ety
    -0.60
     Carls
    -0.57
    POSITIVE LOGITS
    o
    0.65
    ی
    0.61
    al
    0.59
    er
    0.57
    cessive
    0.53
    en
    0.52
    y
    0.51
     '{@
    0.49
    ه
    0.48
    es
    0.48
    Activations Density 0.015%

    No Known Activations