© 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. 1-CLT-HP
    7. 12308
    Prev
    Next
    INDEX
    Explanations

    sectioning

    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
    NameInMap
    -0.80
     myſelf
    -0.73
    StructEnd
    -0.72
     houſe
    -0.69
     itſelf
    -0.66
    rungsseite
    -0.65
     pleaſure
    -0.65
     indisponible
    -0.64
    ſelf
    -0.63
     uſe
    -0.62
    POSITIVE LOGITS
    WithMany
    0.51
     CreateTagHelper
    0.47
     تضيفلها
    0.43
    RenderAtEndOf
    0.43
    fara
    0.40
    InjectAttribute
    0.39
    ⤹
    0.38
     wireType
    0.37
     verle
    0.37
    itoare
    0.36
    Activations Density 1.144%

    No Known Activations