© 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. 45057
    Prev
    Next
    INDEX
    Explanations

    gadgets

    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
    verwijspagina
    -0.82
    WithIOException
    -0.72
    PreInfinity
    -0.66
     complicated
    -0.66
    complicated
    -0.65
     complicate
    -0.65
    Хьажоргаш
    -0.64
     للمعارف
    -0.62
     gadget
    -0.62
     gadgets
    -0.61
    POSITIVE LOGITS
    s
    0.80
    ness
    0.70
    ی
    0.59
    yti
    0.54
    ing
    0.53
    邦
    0.52
    y
    0.51
    er
    0.51
     виправивши
    0.50
    alva
    0.50
    Activations Density 0.088%

    No Known Activations