© 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. 92023
    Prev
    Next
    INDEX
    Explanations

    2

    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
    !
    -0.51
    ↵↵
    -0.49
    ↵
    -0.47
     (
    -0.46
    rott
    -0.46
     PU
    -0.46
      
    -0.45
     R
    -0.45
     -
    -0.44
     Amendment
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.81
     Efq
    0.79
    InjectAttribute
    0.73
     kaynağından
    0.72
     Houſe
    0.72
     faſt
    0.69
    ſelves
    0.69
    ſelf
    0.67
    URLException
    0.67
     himſelf
    0.66
    Activations Density 0.483%

    No Known Activations