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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42463
    Prev
    Next
    INDEX
    Explanations

    Increased

    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
    Reduced
    -0.73
     Reduced
    -0.67
    Enhanced
    -0.60
    Improved
    -0.60
    Increased
    -0.59
     Reinforced
    -0.59
    Increases
    -0.58
     Increased
    -0.57
     Improved
    -0.56
     Enhanced
    -0.56
    POSITIVE LOGITS
     تضيفلها
    1.01
    ing
    0.95
    Personendaten
    0.89
    Datuak
    0.76
     ویکی‌پدی
    0.68
    tagHelperRunner
    0.68
    
    0.68
    ագրություններ
    0.67
    LookAnd
    0.65
    ScopeManager
    0.65
    Activations Density 0.289%

    No Known Activations