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. 11211
    Prev
    Next
    INDEX
    Explanations

    technical/instructions

    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
    Packing
    -0.53
    nd
    -0.53
    Accession
    -0.50
     tema
    -0.50
    таки
    -0.50
    jus
    -0.47
     pilot
    -0.46
     goda
    -0.46
    nt
    -0.46
    やる
    -0.45
    POSITIVE LOGITS
    ThroughAttribute
    0.76
    ParallelGroup
    0.73
    EndContext
    0.69
     defaultstate
    0.67
    MLLoader
    0.66
    OrBuilder
    0.65
     Wicidata
    0.64
     pinulongan
    0.61
     téléphonique
    0.60
     مواليد
    0.59
    Activations Density 0.019%

    No Known Activations