© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13290
    Prev
    Next
    INDEX
    Explanations

    independent

    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
    Autoritní
    -0.74
    Източници
    -0.74
     Independent
    -0.68
     Independ
    -0.66
     independent
    -0.65
    Independent
    -0.65
     Independence
    -0.64
    independent
    -0.63
     发表于
    -0.63
     INDEPENDENT
    -0.63
    POSITIVE LOGITS
     of
    0.70
     from
    0.50
    resave
    0.50
    MergeFrom
    0.48
    ComponentModel
    0.46
     INSTITUTION
    0.46
     minor
    0.45
    cipline
    0.45
    ėl
    0.44
    Perfection
    0.44
    Activations Density 0.082%

    No Known Activations