© 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. 1109
    Prev
    Next
    INDEX
    Explanations

    Time

    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
    ThroughAttribute
    -1.13
    ſelves
    -1.01
     itſelf
    -0.98
     Monfieur
    -0.98
    ſelf
    -0.97
     houſe
    -0.96
     pleaſure
    -0.96
     purpoſe
    -0.96
     Roskov
    -0.94
    StoryboardSegue
    -0.93
    POSITIVE LOGITS
     has
    0.98
     is
    0.65
    has
    0.63
     heeft
    0.62
     hasn
    0.61
     telah
    0.58
     been
    0.56
     have
    0.52
     indicates
    0.51
     является
    0.50
    Activations Density 0.002%

    No Known Activations