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. 74041
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    TableHead
    -0.65
     virš
    -0.62
     ögon
    -0.62
     étoit
    -0.58
     varandra
    -0.57
     semula
    -0.57
    ็จ
    -0.57
     borrar
    -0.54
     eenige
    -0.54
     hjär
    -0.54
    POSITIVE LOGITS
     sett
    0.59
     BoxFit
    0.58
     Plants
    0.56
    InitVars
    0.55
     kasarigan
    0.53
     continúas
    0.53
     Sets
    0.52
     jLabel
    0.52
    __":
    0.51
     Set
    0.51
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.