© 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. 3966
    Prev
    Next
    INDEX
    Explanations

    references to recording studios or studio-related terminology

    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
    TOBER
    -0.63
    strate
    -0.57
    ɯ
    -0.57
     Dumas
    -0.56
     bawang
    -0.56
    стви
    -0.55
     statis
    -0.55
     Molière
    -0.54
    Oby
    -0.54
    AppComponent
    -0.53
    POSITIVE LOGITS
     studio
    3.92
     Studio
    3.52
    studio
    3.47
    Studio
    3.39
     studios
    3.28
     STUDIO
    3.20
     Studios
    2.95
    STUDIO
    2.94
    studios
    2.53
    Studios
    2.39
    Activations Density 0.005%

    No Known Activations