© 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. 91942
    Prev
    Next
    INDEX
    Explanations

    yes

    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
     yes
    -1.64
     yeah
    -1.16
    yes
    -1.15
     YES
    -1.03
     Yes
    -1.02
    Yes
    -0.98
     yea
    -0.94
     yep
    -0.92
    YES
    -0.91
    yeah
    -0.90
    POSITIVE LOGITS
    onsored
    0.63
     oprot
    0.63
    ukone
    0.59
     виправивши
    0.59
    StructEnd
    0.57
    paka
    0.56
     Pingback
    0.55
    goti
    0.54
    letoe
    0.54
    InstrumentedTest
    0.54
    Activations Density 0.465%

    No Known Activations