© 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. 4-CLT-HP
    7. 4928
    Prev
    Next
    INDEX
    Explanations

    they

    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
    ValueStyle
    -0.87
     Réponses
    -0.84
     disponibilités
    -0.77
    BeginContext
    -0.71
    IntoConstraints
    -0.71
    HttpFoundation
    -0.70
     resourceCulture
    -0.68
     pylab
    -0.67
    RegressionTest
    -0.67
     HasFactory
    -0.66
    POSITIVE LOGITS
    <bos>
    0.78
    UnsafeEnabled
    0.45
    findpost
    0.43
    !*\
    0.42
     }))
    0.41
     chaves
    0.40
    KURZBESCHREIBUNG
    0.40
     chave
    0.38
    /**
    0.38
     PhpStorm
    0.37
    Activations Density 0.012%

    No Known Activations