© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2011
    Prev
    Next
    INDEX
    Explanations

    fame

    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
    __(/*!
    -0.73
    RepeatedField
    -0.66
    DIPSETTING
    -0.64
    Geplaatst
    -0.59
     RoutedEventArgs
    -0.59
    matchCondition
    -0.57
     typelib
    -0.57
    ijų
    -0.56
     CommonModule
    -0.56
     CreateTagHelper
    -0.56
    POSITIVE LOGITS
     fréquence
    0.55
    éviter
    0.54
     inimes
    0.52
     temporales
    0.51
     stră
    0.51
    Cubit
    0.51
     mijne
    0.51
     jueces
    0.50
     bénéficier
    0.50
     Waray
    0.49
    Activations Density 0.004%

    No Known Activations