© 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. 8-RES-MATRYOSHKA-DC
    7. 29412
    Prev
    Next
    INDEX
    Explanations

    the word "above"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -0.57
     it
    -0.57
     below
    -0.56
     THIS
    -0.54
     beneath
    -0.52
    timmen
    -0.52
     Alat
    -0.52
     krist
    -0.51
    currentValue
    -0.51
     the
    -0.51
    POSITIVE LOGITS
    antMatchers
    1.00
    BeginContext
    0.88
     kasarigan
    0.88
    клопе
    0.88
    
    0.84
    CloseOperation
    0.83
    windowFixed
    0.81
    colgroup
    0.81
    OGND
    0.81
     المعيارى
    0.81
    Activations Density 0.007%

    No Known Activations