© 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. 2141
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     CreateTagHelper
    -0.90
     Paglinawan
    -0.81
     Shakspeare
    -0.79
     Exactos
    -0.77
     kasarigan
    -0.75
    BeginContext
    -0.73
    SourceChecksum
    -0.69
     يتيمه
    -0.68
     Anſ
    -0.68
     صوتيه
    -0.67
    POSITIVE LOGITS
    ,
    0.49
    crumbs
    0.49
     some
    0.46
     these
    0.44
    some
    0.44
    gewä
    0.42
     is
    0.42
     wells
    0.42
    されました
    0.41
     men
    0.41
    Activations Density 0.005%

    No Known Activations