© 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. 62
    Prev
    Next
    INDEX
    Explanations

    references to experimental control conditions

    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
     allé
    -0.57
     Masyarakat
    -0.57
    omitempty
    -0.56
    brengen
    -0.56
     JOURNEY
    -0.54
     itinéraire
    -0.53
    getInputStream
    -0.52
     engagé
    -0.51
    σιν
    -0.50
     partagé
    -0.50
    POSITIVE LOGITS
     control
    4.44
     Control
    4.09
    control
    4.03
    Control
    3.88
     CONTROL
    3.83
     controls
    3.55
    CONTROL
    3.48
     Controls
    3.25
     controlling
    3.23
     controle
    3.08
    Activations Density 2.273%

    No Known Activations