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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40774
    Prev
    Next
    INDEX
    Explanations

    volumetric

    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
    boxes
    -0.67
    sizeCache
    -0.67
    帖最后由
    -0.61
     שוליים
    -0.61
    WebServlet
    -0.58
    CppMethod
    -0.57
    
    -0.57
     vectorielle
    -0.55
     judiciales
    -0.55
     pelican
    -0.54
    POSITIVE LOGITS
    ities
    0.63
    ization
    0.60
    izing
    0.59
    ancy
    0.58
    izations
    0.57
    ized
    0.56
    abestanden
    0.54
    ulation
    0.54
    istic
    0.54
    ario
    0.54
    Activations Density 0.578%

    No Known Activations