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. 74070
    Prev
    Next
    INDEX
    Explanations

    Text snippets

    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
    ExtendWith
    -0.57
    protoimpl
    -0.56
    Parcelize
    -0.55
     gyhoeddwyd
    -0.54
    RegressionTest
    -0.51
    userdetails
    -0.51
    canestro
    -0.50
    FieldDescriptor
    -0.49
    ArrowToggle
    -0.48
    readystatechange
    -0.48
    POSITIVE LOGITS
    Datuak
    0.59
    pers
    0.56
     amitié
    0.55
     Wint
    0.52
    bury
    0.52
    ionario
    0.51
     CWE
    0.51
    ómico
    0.50
     AttributeSet
    0.50
    íncipe
    0.49
    Activations Density 0.000%

    No Known Activations