© 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. 94993
    Prev
    Next
    INDEX
    Explanations

    blog

    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
    StoryboardSegue
    -0.81
     fevere
    -0.81
     raiſ
    -0.80
     purpoſe
    -0.79
     uſed
    -0.79
     fubject
    -0.74
     Monfieur
    -0.73
     tranſ
    -0.70
     myſelf
    -0.69
     obſ
    -0.69
    POSITIVE LOGITS
     $
    0.54
     thiệu
    0.51
     çar
    0.46
    зий
    0.44
    {$
    0.44
    mV
    0.44
    W
    0.42
    ː
    0.42
     W
    0.42
     perdere
    0.41
    Activations Density 0.002%

    No Known Activations