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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13640
    Prev
    Next
    INDEX
    Explanations

    how

    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
    elemField
    -0.68
    EndContext
    -0.65
    PROTOBUF
    -0.65
     незавершена
    -0.58
     πως
    -0.57
    InjectAttribute
    -0.54
    enderror
    -0.53
    клопе
    -0.53
    TextAppearance
    -0.52
     mergeFrom
    -0.51
    POSITIVE LOGITS
    such
    0.57
    Such
    0.57
     '..
    0.55
     legitimacy
    0.55
     Such
    0.53
     esternos
    0.53
     AssemblyTitle
    0.52
     credibility
    0.49
    IRQn
    0.49
     such
    0.48
    Activations Density 0.009%

    No Known Activations