© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5066
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, organizations, or events

    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
    InvalidProtocol
    -0.56
     United
    -0.51
     États
    -0.48
     Etats
    -0.47
     italianos
    -0.46
     IBOutlet
    -0.46
     Estados
    -0.42
    PhysRev
    -0.41
    figsize
    -0.40
     grpc
    -0.40
    POSITIVE LOGITS
     kaynağından
    0.77
    //};
    0.72
     NUKAT
    0.71
    contentLoaded
    0.71
     الحره
    0.67
    μβρίου
    0.67
     ++)
    0.66
    }>;
    0.65
    ]--;
    0.65
    (!__
    0.65
    Activations Density 0.586%

    No Known Activations