© 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. 5-CLT-HP
    7. 2154
    Prev
    Next
    INDEX
    Explanations

    able

    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
     AssemblyCulture
    -0.81
    oa̍t
    -0.62
     فريبيس
    -0.60
    ########.
    -0.60
    styleType
    -0.59
     للاسماء
    -0.59
    ViewStyle
    -0.58
    клопе
    -0.57
     InputDecoration
    -0.56
     noDo
    -0.56
    POSITIVE LOGITS
    MockBean
    0.57
    '){
    0.56
    )),
    0.50
    StoreMessageInfo
    0.50
    "+
    0.49
     ifrån
    0.49
    '),
    0.49
     besök
    0.48
    ambilan
    0.48
     \\
    0.48
    Activations Density 0.147%

    No Known Activations