© 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. 3530
    Prev
    Next
    INDEX
    Explanations

    Code, URLs, incomplete words

    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
    +#+#
    -0.75
    setVerticalGroup
    -0.74
    Autoritní
    -0.72
    MessageOf
    -0.70
     ExecuteAsync
    -0.69
     nonatomic
    -0.68
    ContentAlignment
    -0.68
    TagHelpers
    -0.68
    GraphicsUnit
    -0.68
     للمعارف
    -0.64
    POSITIVE LOGITS
     käns
    0.40
     jaren
    0.40
     varandra
    0.39
    etka
    0.39
     suivants
    0.36
     ansiedade
    0.36
     dėl
    0.35
     ahor
    0.35
     narci
    0.35
     lèvres
    0.35
    Activations Density 0.001%

    No Known Activations