© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40620
    Prev
    Next
    INDEX
    Explanations

    preach

    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
     controllers
    -0.69
     Controllers
    -0.57
     controller
    -0.57
     Controller
    -0.56
    legg
    -0.56
     jails
    -0.54
     gauges
    -0.54
     zoll
    -0.54
    ing
    -0.52
     predators
    -0.52
    POSITIVE LOGITS
     Савезне
    0.74
     peindre
    0.73
    enumi
    0.71
     lèvres
    0.69
    GHIJKLM
    0.69
     cérami
    0.68
     eccell
    0.68
    grà
    0.65
    ConfigureAwait
    0.65
    TestingModule
    0.62
    Activations Density 0.040%

    No Known Activations