Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73873
    Prev
    Next
    INDEX
    Explanations

    Technical/varied contexts

    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
    QMetaType
    -0.72
    ViewImports
    -0.57
    expandindo
    -0.57
     Tine
    -0.53
     CreateTagHelper
    -0.52
     InputDecoration
    -0.52
    AddTagHelper
    -0.51
    Sucesor
    -0.50
    ollectionView
    -0.49
    DrawerToggle
    -0.49
    POSITIVE LOGITS
    liato
    0.48
     Sweeney
    0.47
    FromArgb
    0.46
     scores
    0.46
    ordning
    0.46
     London
    0.46
    api
    0.46
     franchises
    0.46
    r
    0.45
    avan
    0.45
    Activations Density 0.000%

    No Known Activations