© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3338
    Prev
    Next
    INDEX
    Explanations

    the word "leader" and related terms such as "leadership".

    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
    Negative Logits
    ParallelGroup
    -0.69
     lead
    -0.58
    тере
    -0.54
     Leads
    -0.54
     المح
    -0.52
    TextWatcher
    -0.52
    กรม
    -0.52
     emf
    -0.51
     Ingen
    -0.51
     cos
    -0.50
    POSITIVE LOGITS
     leaders
    2.52
     Leaders
    2.42
    Leaders
    2.42
     leader
    2.39
     Leader
    2.27
    leaders
    2.27
    Leader
    2.20
    leader
    2.17
     leadership
    2.08
     LEADER
    2.05
    Activations Density 0.021%

    No Known Activations