© 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. 12108
    Prev
    Next
    INDEX
    Explanations

    the concept of a conditioned or "trained" state or process

    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
    odynamic
    -0.75
     sanction
    -0.68
    obacz
    -0.55
     ")");
    -0.55
     hypothalam
    -0.53
    AllAfrica
    -0.53
     hinaus
    -0.52
    odynamics
    -0.51
    Chham
    -0.51
     Leviathan
    -0.51
    POSITIVE LOGITS
     conditioned
    1.72
    conditioned
    1.59
    pak
    0.92
     Pak
    0.79
    Clik
    0.76
    Pak
    0.75
     Exacts
    0.74
    DeleteBehavior
    0.68
     pak
    0.67
     EconPapers
    0.66
    Activations Density 0.002%

    No Known Activations