© 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. 11564
    Prev
    Next
    INDEX
    Explanations

    instrumentation

    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
     oprot
    -0.63
     OFDb
    -0.61
    省市镇
    -0.60
    MessageOf
    -0.59
    ylus
    -0.58
    herzog
    -0.57
     equality
    -0.56
    transQ
    -0.56
    :✨
    -0.55
    rocco
    -0.54
    POSITIVE LOGITS
     inequalities
    1.10
    Instrumentation
    1.06
     abusive
    0.96
     Inequalities
    0.83
     instrumentation
    0.76
     Instrumentation
    0.74
     -,
    0.74
    gravity
    0.65
    BIO
    0.63
     BIO
    0.61
    Activations Density 0.006%

    No Known Activations