© 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. 5894
    Prev
    Next
    INDEX
    Explanations

    references to academic papers

    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
     metal
    -0.74
     metall
    -0.70
     METAL
    -0.69
    metal
    -0.67
     bronze
    -0.66
     Metall
    -0.66
    Metal
    -0.65
     Metal
    -0.65
     Bronze
    -0.64
    bronze
    -0.63
    POSITIVE LOGITS
     paper
    3.64
     Paper
    3.47
    Paper
    3.39
    paper
    3.36
     PAPER
    3.22
    PAPER
    2.81
     papers
    2.66
     Papers
    2.53
    papers
    2.47
    Papers
    2.33
    Activations Density 0.087%

    No Known Activations