© 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. 1125
    Prev
    Next
    INDEX
    Explanations

    evening

    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
     Evening
    -1.06
    Evening
    -1.03
    evening
    -0.99
     evening
    -0.98
    ########.
    -0.87
    CppMethod
    -0.84
     EVENING
    -0.84
    ChildScrollView
    -0.78
    
    -0.75
     avond
    -0.73
    POSITIVE LOGITS
    .,
    0.54
    ated
    0.53
    ucs
    0.52
    ic
    0.51
    ️
    0.51
    ott
    0.50
    ul
    0.50
    hren
    0.49
    acus
    0.48
    .
    0.48
    Activations Density 0.133%

    No Known Activations