© 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. 0-CLT-HP
    4. 38388
    Prev
    Next
    INDEX
    Explanations

    ardin

    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
    ########.
    -0.94
    ardin
    -0.88
     ligiloj
    -0.65
    OGND
    -0.63
    LookAnd
    -0.62
    cloudfront
    -0.62
    oneofs
    -0.60
     تضيفلها
    -0.60
    ⓧ
    -0.59
    PerformLayout
    -0.56
    POSITIVE LOGITS
     hinweg
    0.57
    存于互联网档案馆
    0.57
    ')";
    0.55
    PYX
    0.55
     []),
    0.52
    pecker
    0.50
    <?=$
    0.49
    [++
    0.49
    StoryboardSegue
    0.49
    mec
    0.48
    Activations Density 0.034%

    No Known Activations