© 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. 1-CLT-HP
    7. 45646
    Prev
    Next
    INDEX
    Explanations

    refrigeration

    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
     refrigerator
    -0.71
     refrigerate
    -0.71
    Refriger
    -0.68
     Refrigerator
    -0.62
     Refriger
    -0.61
     refrigerators
    -0.60
    refriger
    -0.59
     fridge
    -0.58
    фильм
    -0.54
     Fridge
    -0.54
    POSITIVE LOGITS
    LookAnd
    0.70
    CodeAttribute
    0.66
    <?
    0.57
    AntiForgeryToken
    0.56
     protoimpl
    0.55
     Мексичка
    0.55
    ########.
    0.55
    sizeCache
    0.54
    ArgsConstructor
    0.54
    iotensin
    0.52
    Activations Density 0.017%

    No Known Activations