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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92697
    Prev
    Next
    INDEX
    Explanations

    Respon

    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
     Respon
    -0.72
    NavController
    -0.64
    SharedCtor
    -0.63
     resourceCulture
    -0.62
    下载附件
    -0.59
    andExpect
    -0.58
    ParallelGroup
    -0.57
     مشين
    -0.56
    IVEREF
    -0.56
    \{\\
    -0.56
    POSITIVE LOGITS
    NUMX
    0.55
    StateToProps
    0.49
    shed
    0.48
      (
    0.48
    ERSHIP
    0.47
    dedores
    0.46
    ViewImports
    0.46
    GHIJKLM
    0.45
    dles
    0.45
    ++
    0.44
    Activations Density 0.683%

    No Known Activations