© 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. 1-CLT-HP
    7. 13203
    Prev
    Next
    INDEX
    Explanations

    2

    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
     autorytatywna
    -0.85
    Autoritní
    -0.75
     dieux
    -0.75
     חיצוניים
    -0.74
    elemField
    -0.74
     typelib
    -0.73
     Administrativna
    -0.71
     CreateTagHelper
    -0.70
     vérit
    -0.69
     للمعارف
    -0.68
    POSITIVE LOGITS
    ”
    0.61
    "
    0.59
     leva
    0.52
    "-
    0.52
    ”-
    0.51
     lifts
    0.50
     oz
    0.49
     drains
    0.49
     shells
    0.48
     cups
    0.48
    Activations Density 0.017%

    No Known Activations