Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 39510
    Prev
    Next
    INDEX
    Explanations

    intelligent

    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
     W
    -0.82
    W
    -0.72
     smart
    -0.66
     sensible
    -0.66
    smart
    -0.63
     Smart
    -0.60
    Smart
    -0.60
    intelligent
    -0.60
    发表于
    -0.55
    logical
    -0.53
    POSITIVE LOGITS
    WebVitals
    0.80
    ness
    0.65
    下载附件
    0.58
    EndGlobalSection
    0.57
     endforeach
    0.56
     betweenstory
    0.56
    lapsingToolbar
    0.55
    jsonwebtoken
    0.54
    Eksterne
    0.53
    StoryboardSegue
    0.53
    Activations Density 0.076%

    No Known Activations