© 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. 0-RES-MATRYOSHKA-DC
    7. 12306
    Prev
    Next
    INDEX
    Explanations

    references to concepts or entities associated with military, political, or conflict contexts

    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
     defaultstate
    -0.77
    ftagPool
    -0.75
    Personensuche
    -0.64
     الرياضيه
    -0.60
     shallo
    -0.59
    expandindo
    -0.58
     AssemblyCompany
    -0.57
    ########.
    -0.57
     corporativa
    -0.56
    ніципа
    -0.56
    POSITIVE LOGITS
    pple
    1.73
    ppled
    1.35
    pples
    1.20
    ppling
    1.11
     Guan
    0.91
     mili
    0.87
    guan
    0.85
    unct
    0.81
     guan
    0.76
    Mili
    0.73
    Activations Density 0.005%

    No Known Activations