© 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. 6909
    Prev
    Next
    INDEX
    Explanations

    references to dramatic themes or elements in content

    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
    cyclo
    -0.60
    romyalgia
    -0.60
    abetes
    -0.59
     crusher
    -0.59
    psack
    -0.58
    Extinguishing
    -0.58
     Dij
    -0.58
     Doodle
    -0.57
    }^{+\
    -0.57
    AndEndTag
    -0.57
    POSITIVE LOGITS
     drama
    2.72
     dramatic
    2.52
     Dramatic
    2.42
    drama
    2.38
    dramatic
    2.38
     Drama
    2.34
    Drama
    2.34
    Dramatic
    2.31
     dram
    2.09
     dramas
    2.08
    Activations Density 0.075%

    No Known Activations