© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93176
    Prev
    Next
    INDEX
    Explanations

    Monarch

    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
     Fish
    -0.55
    aggressive
    -0.54
     aggressive
    -0.52
    WebServlet
    -0.50
    sterious
    -0.49
     ویکی‌پدیای
    -0.48
    stateMutability
    -0.47
    }]$
    -0.46
    igraph
    -0.46
    simage
    -0.46
    POSITIVE LOGITS
    s
    1.13
    ی
    0.77
    y
    0.74
    e
    0.72
     StringTokenizer
    0.67
     Eſ
    0.61
     Majefty
    0.60
     againſt
    0.60
    a
    0.59
    es
    0.58
    Activations Density 1.340%

    No Known Activations