© 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. 0-CLT-HP
    7. 44077
    Prev
    Next
    INDEX
    Explanations

    education and memorials

    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
     messages
    -0.74
     Messages
    -0.67
     Messaging
    -0.60
     messaging
    -0.57
    Messages
    -0.56
    ագրություններ
    -0.56
     مرئيه
    -0.55
     Wartawan
    -0.54
    帖最后由
    -0.54
    messages
    -0.53
    POSITIVE LOGITS
    SpringBoot
    0.58
    RunAsync
    0.57
     tå
    0.54
     Richelieu
    0.54
    haup
    0.52
    UserScript
    0.52
    envolvimento
    0.52
     Wich
    0.50
    )\}
    0.49
     basah
    0.49
    Activations Density 1.190%

    No Known Activations