© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 6257
    Prev
    Next
    INDEX
    Explanations

    references to a specific high-ranking organizational position

    oai_token-act-pair · gpt-4.1-nano
    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
    Rüyada
    -0.61
     tutor
    -0.58
     посо
    -0.56
     Chwiliwch
    -0.55
     فريبيس
    -0.54
     lecturer
    -0.53
    adaptiveStyles
    -0.52
     Pilate
    -0.52
    HasForeignKey
    -0.51
     lecturers
    -0.51
    POSITIVE LOGITS
    Chief
    3.38
     Chief
    3.36
     chief
    3.23
    chief
    3.05
     CHIEF
    3.03
     chiefs
    2.33
     Chiefs
    2.25
    chiefs
    2.05
    首席
    1.51
     chieftain
    1.44
    Activations Density 0.013%

    No Known Activations