© 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. 43957
    Prev
    Next
    INDEX
    Explanations

    Names and abbreviations

    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
     BO
    -0.65
    ++){
    -0.61
    BO
    -0.57
     referenties
    -0.57
     SO
    -0.54
    }")
    -0.52
     AB
    -0.51
     Trent
    -0.51
    hton
    -0.51
    ++)
    -0.49
    POSITIVE LOGITS
    DockStyle
    0.84
    AnchorStyles
    0.83
    GraphicsUnit
    0.72
     raiſ
    0.71
     MessageBoxIcon
    0.71
     GenerationType
    0.70
    ReusableCell
    0.69
     himſelf
    0.69
     itſelf
    0.69
    reportWebVitals
    0.68
    Activations Density 0.124%

    No Known Activations