© 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. 1-CLT-HP
    4. 12102
    Prev
    Next
    INDEX
    Explanations

    scientific and medical texts

    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
    +#+#
    -0.86
     Acres
    -0.82
    はじめに
    -0.75
     FetchType
    -0.74
     acres
    -0.73
     HasFactory
    -0.71
    acres
    -0.69
    WriteBarrier
    -0.66
    Diwedd
    -0.66
     lenker
    -0.65
    POSITIVE LOGITS
    hwar
    0.41
     برانيه
    0.39
     seorang
    0.38
     rusa
    0.38
     composição
    0.38
    JAKARTA
    0.38
    lą
    0.38
     russe
    0.37
    startX
    0.37
     parceiros
    0.36
    Activations Density 0.010%

    No Known Activations