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. 39235
    Prev
    Next
    INDEX
    Explanations

    tables and references

    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
    eleste
    -0.66
    mybatisplus
    -0.63
    RectangleBorder
    -0.63
    orkin
    -0.60
    addContainerGap
    -0.59
    bootstrapcdn
    -0.57
     pinulongan
    -0.57
     vuitton
    -0.56
     متعلقه
    -0.54
    celotti
    -0.54
    POSITIVE LOGITS
    ↵↵
    0.75
     
    0.73
    .
    0.66
     A
    0.57
    <strong>
    0.49
     I
    0.48
    2
    0.47
    Demografia
    0.47
    ↵
    0.46
      
    0.46
    Activations Density 0.103%

    No Known Activations