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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91085
    Prev
    Next
    INDEX
    Explanations

    Petroleum

    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
    cox
    -0.73
     Petroleum
    -0.60
    Cox
    -0.59
    PreferredItem
    -0.55
    ly
    -0.53
     tires
    -0.52
     Cox
    -0.51
     cri
    -0.49
    iti
    -0.48
     sel
    -0.48
    POSITIVE LOGITS
    enumi
    0.71
    +#+#
    0.70
    tableFuture
    0.66
     Efq
    0.65
     GoogleFonts
    0.65
     ſaid
    0.65
     Houſe
    0.64
     дописавши
    0.63
     Theſe
    0.63
    zondere
    0.62
    Activations Density 0.360%

    No Known Activations