© 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. 1-RES-MATRYOSHKA-DC
    7. 25
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or groups, often indicating possession or association

    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
     Athenians
    -0.70
     Sopho
    -0.69
     Agamemnon
    -0.68
     aikana
    -0.67
     Mep
    -0.67
     Normdatei
    -0.65
    DockStyle
    -0.62
     оно
    -0.59
     vectorielle
    -0.59
     Plenum
    -0.58
    POSITIVE LOGITS
     their
    2.61
     his
    2.39
     our
    2.28
     your
    2.19
     its
    2.13
    their
    2.13
     my
    2.03
     her
    1.96
     THEIR
    1.91
     ihrer
    1.85
    Activations Density 1.853%

    No Known Activations