© 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. 4-CLT-HP
    7. 3463
    Prev
    Next
    INDEX
    Explanations

    changing, processing

    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
     work
    -0.51
     and
    -0.49
    AnchorTagHelper
    -0.48
     tasks
    -0.46
     &
    -0.46
    ims
    -0.44
     steps
    -0.44
    Παραπομπές
    -0.44
     discussions
    -0.44
    ÕES
    -0.41
    POSITIVE LOGITS
    printStackTrace
    0.70
    BeginInit
    0.68
     BorderRadius
    0.67
    makeConstraints
    0.66
    èdia
    0.66
     nakalista
    0.65
    ImageContext
    0.63
    帖最后由
    0.63
     réessayer
    0.61
     AspNetCore
    0.61
    Activations Density 0.016%

    No Known Activations