© 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. 40141
    Prev
    Next
    INDEX
    Explanations

    bipolar

    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
    world
    -0.83
    World
    -0.82
    force
    -0.57
    cshtml
    -0.56
    sha
    -0.50
    P
    -0.49
    Elements
    -0.48
    WORLD
    -0.47
     Welt
    -0.46
    worlds
    -0.45
    POSITIVE LOGITS
     MainAxisSize
    0.91
    __':
    
    0.82
    Portail
    0.79
    gorithm
    0.73
    +:+
    0.72
    +#+
    0.69
    Thiết
    0.68
    Datuak
    0.65
    NUMX
    0.64
    arraycopy
    0.64
    Activations Density 0.081%

    No Known Activations