© 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. 0-CLT-HP
    7. 38984
    Prev
    Next
    INDEX
    Explanations

    Tests

    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
    van
    -0.61
    ậu
    -0.59
     Sharon
    -0.54
    urement
    -0.53
    ipfel
    -0.51
    redos
    -0.51
    middlewares
    -0.51
    helo
    -0.51
    ubble
    -0.50
    vismo
    -0.50
    POSITIVE LOGITS
    Sucesor
    0.68
     nahilalakip
    0.66
    RenderAtEndOf
    0.66
    principalTable
    0.60
    новниш
    0.58
    ValueGeneration
    0.58
    addContainerGap
    0.57
    SourceChecksum
    0.56
    PerformLayout
    0.56
    AddTagHelper
    0.56
    Activations Density 1.878%

    No Known Activations