Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12500
    Prev
    Next
    INDEX
    Explanations

    oil and gas

    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
     CWE
    -0.68
    WithIOException
    -0.61
     /\.
    -0.61
    UserScript
    -0.60
     utafitiHapana
    -0.60
    astify
    -0.55
     trajets
    -0.55
    enoord
    -0.55
     kasarigan
    -0.54
     viewDidLoad
    -0.54
    POSITIVE LOGITS
    +:+
    0.48
     nakalista
    0.47
    eabouts
    0.46
    strijd
    0.45
    chee
    0.45
    ortheast
    0.45
    -------
    0.45
    SSON
    0.44
    ربای
    0.43
    igot
    0.42
    Activations Density 0.020%

    No Known Activations