© 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. 4-CLT-HP
    7. 3388
    Prev
    Next
    INDEX
    Explanations

    technical/code related

    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
     CommonModule
    -0.56
     wasp
    -0.55
     moth
    -0.54
    ########.
    -0.52
    idenav
    -0.52
     noqa
    -0.52
     wasps
    -0.51
    UnusedPrivate
    -0.51
     hornet
    -0.50
    GEBURTS
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    0.61
    RegistryLite
    0.61
    Datuak
    0.56
    
    0.49
     AssemblyCulture
    0.49
     rechange
    0.48
     bicchiere
    0.48
    boven
    0.47
    enterOuterAlt
    0.47
    bend
    0.47
    Activations Density 0.001%

    No Known Activations