© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40267
    Prev
    Next
    INDEX
    Explanations

    ability, functionality

    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
    -0.88
     Capacity
    -0.84
    Capacity
    -0.80
     capacities
    -0.78
     CAPACITY
    -0.76
     appropriate
    -0.73
     capable
    -0.72
    capable
    -0.72
    capacity
    -0.71
     Capabilities
    -0.71
    POSITIVE LOGITS
    PerformLayout
    0.83
    ագրություններ
    0.73
    WebElementEntity
    0.65
     AttributeSet
    0.61
    HtmlAttribute
    0.60
     Saddle
    0.58
    новништво
    0.57
    FontOfSize
    0.56
    Lähteet
    0.56
     Савезне
    0.55
    Activations Density 1.697%

    No Known Activations