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. 1-CLT-HP
    4. 11041
    Prev
    Next
    INDEX
    Explanations

    hold

    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
     suivantes
    -0.56
    ksessa
    -0.52
     henkil
    -0.51
     kyse
    -0.50
     vectoriales
    -0.50
    berdayakan
    -0.49
     jossa
    -0.49
    holdet
    -0.48
    setViewName
    -0.48
     hold
    -0.48
    POSITIVE LOGITS
    تقاوى
    0.71
     Signalez
    0.59
    ISupport
    0.57
    atsun
    0.56
     Universe
    0.54
     backs
    0.54
    abestanden
    0.53
     back
    0.53
     universe
    0.52
    universe
    0.52
    Activations Density 0.005%

    No Known Activations