© 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. 1127
    Prev
    Next
    INDEX
    Explanations

    a

    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
     lot
    -0.68
     PopupWindow
    -0.65
     StatefulWidget
    -0.59
    AnimationsModule
    -0.58
     onCreateView
    -0.57
     UITextField
    -0.56
     LOT
    -0.55
    EndContext
    -0.55
    mybatisplus
    -0.55
    CloseOperation
    -0.53
    POSITIVE LOGITS
     spese
    0.66
     igång
    0.66
     sortes
    0.63
     traités
    0.63
     quantità
    0.61
     règlement
    0.59
     flesta
    0.58
     händer
    0.57
     ögon
    0.57
     traité
    0.57
    Activations Density 0.079%

    No Known Activations