© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96148
    Prev
    Next
    INDEX
    Explanations

    code or technical documentation

    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
    AccessorTable
    -0.89
    IndentedString
    -0.81
    TagMode
    -0.74
     betweenstory
    -0.73
    sizeCache
    -0.71
    Personensuche
    -0.70
    IBarButtonItem
    -0.68
    CodedInputStream
    -0.68
     تضيفلها
    -0.68
     pinulongan
    -0.68
    POSITIVE LOGITS
     past
    0.51
     after
    0.50
     road
    0.49
     path
    0.49
     once
    0.48
     spec
    0.47
     long
    0.47
     U
    0.46
     fabric
    0.45
    FormsModule
    0.45
    Activations Density 0.002%

    No Known Activations