© 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. 5-CLT-HP
    7. 2016
    Prev
    Next
    INDEX
    Explanations

    open

    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
     autorytatywna
    -0.81
     HasFactory
    -0.79
    Personensuche
    -0.74
    Personendaten
    -0.69
    hyrchwyd
    -0.67
    queryInterface
    -0.67
    IUrlHelper
    -0.66
    oredCriteria
    -0.64
     дописавши
    -0.63
    aarrggbb
    -0.62
    POSITIVE LOGITS
     réessayer
    0.53
    smarty
    0.46
    tillinger
    0.45
    økt
    0.45
    новништво
    0.42
    ències
    0.42
    arele
    0.42
    staticmethod
    0.42
    hubung
    0.42
    roek
    0.40
    Activations Density 0.004%

    No Known Activations