© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13099
    Prev
    Next
    INDEX
    Explanations

    capacity

    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
     capacity
    -0.93
     Capacity
    -0.84
    capacity
    -0.82
    Capacity
    -0.79
     capacities
    -0.65
     CAPACITY
    -0.65
     capacidad
    -0.63
    awtextra
    -0.61
     capacité
    -0.61
     kapasitas
    -0.49
    POSITIVE LOGITS
     itſelf
    0.81
     themſelves
    0.79
     houſe
    0.77
     myſelf
    0.77
    chtenstein
    0.73
     surla
    0.67
     cauſe
    0.67
     purpoſe
    0.67
    uxxxx
    0.66
    WebElementEntity
    0.66
    Activations Density 0.008%

    No Known Activations