© 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. 7186
    Prev
    Next
    INDEX
    Explanations

    consensus or standard language patterns related to review standards or formal evaluations

    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
    >";
    -0.70
    AddTagHelper
    -0.67
    ;");
    -0.63
    >";
    -0.62
    }";
    -0.62
    gie
    -0.60
    '",
    -0.60
     ]
    -0.60
    =";
    -0.57
    ()]
    -0.57
    POSITIVE LOGITS
     resourceCulture
    0.73
     Waray
    0.66
     pleaf
    0.64
     pleaſure
    0.64
     MatDialog
    0.63
     ftate
    0.59
     Majefty
    0.59
     cherchés
    0.59
     caufe
    0.59
     anſ
    0.58
    Activations Density 0.108%

    No Known Activations