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. 20-CLT-HP
    4. 74083
    Prev
    Next
    INDEX
    Explanations

    code and technical descriptions

    np_max-act-logits · 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
     resourceCulture
    -0.92
     препратки
    -0.85
     سكانية
    -0.72
    ContentAsync
    -0.64
     Reverso
    -0.63
     tartalomajánló
    -0.61
    +#+#
    -0.60
     Савезне
    -0.58
    âce
    -0.56
     onCreateView
    -0.56
    POSITIVE LOGITS
    oopy
    0.45
    -\
    0.42
    author
    0.42
    Bull
    0.42
    [['
    0.41
    Availability
    0.41
     junit
    0.41
    wasm
    0.40
    νης
    0.40
     Zweiten
    0.40
    Activations Density 0.005%

    No Known Activations