© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2672
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     myſelf
    -0.64
     ویکی‌پدیا
    -0.63
    -------------</
    -0.60
    $")
    -0.56
    BrowserModule
    -0.56
     occafion
    -0.56
     ')'
    -0.56
    HomeAsUpEnabled
    -0.54
     theſe
    -0.53
    vière
    -0.53
    POSITIVE LOGITS
     
    0.60
    ValueStyle
    0.50
     of
    0.50
     TextAppearance
    0.47
     ferons
    0.44
    okovic
    0.43
     vectorielle
    0.43
     PRP
    0.42
    agne
    0.41
    neté
    0.41
    Activations Density 0.028%

    No Known Activations