© 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. 6493
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinion or self-assessment

    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
     “
    -0.54
    o
    -0.54
    って
    -0.52
    bukkit
    -0.49
     Williams
    -0.49
     the
    -0.48
    CMS
    -0.47
    a
    -0.47
     previously
    -0.46
    Williams
    -0.46
    POSITIVE LOGITS
     am
    2.36
     Am
    1.69
    Am
    1.55
     AM
    1.01
    am
    0.98
     ам
    0.92
     Amm
    0.85
     Ам
    0.83
     ujednoznacz
    0.81
     हूं
    0.79
    Activations Density 0.021%

    No Known Activations