© 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. 4324
    Prev
    Next
    INDEX
    Explanations

    see

    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
    ness
    -0.71
    nya
    -0.67
    Portale
    -0.62
    shire
    -0.57
    に
    -0.56
    sof
    -0.54
    sheng
    -0.53
     PropTypes
    -0.52
    으로
    -0.50
    sad
    -0.50
    POSITIVE LOGITS
    ma
    0.68
    thing
    0.64
    kee
    0.57
    grass
    0.55
    WriteTagHelper
    0.55
    go
    0.54
    ground
    0.54
     fourrure
    0.53
    ger
    0.52
    Mee
    0.52
    Activations Density 0.005%

    No Known Activations