© 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. 12164
    Prev
    Next
    INDEX
    Explanations

    Horses, dance, mansions

    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
     mares
    -1.02
     mare
    -0.97
    InjectAttribute
    -0.77
     stallion
    -0.69
    expandindo
    -0.60
     Mares
    -0.58
    
    -0.58
    addPreferredGap
    -0.58
     IBOutlet
    -0.57
    SharedDtor
    -0.57
    POSITIVE LOGITS
     متحده
    0.59
    PhysRev
    0.51
    ship
    0.49
    protoimpl
    0.49
    soort
    0.47
    salt
    0.47
    люс
    0.46
     ModelExpression
    0.46
    AndroidJUnit
    0.46
    |}{$
    0.46
    Activations Density 0.012%

    No Known Activations