© 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. 0-RES-MATRYOSHKA-DC
    7. 11454
    Prev
    Next
    INDEX
    Explanations

    references to explicit references to sexual acts or sexual 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
    ED
    -1.85
     ED
    -1.45
    ced
    -1.02
    eds
    -0.98
    EDS
    -0.86
    ted
    -0.85
    sed
    -0.84
    CED
    -0.84
    EDA
    -0.78
    EDE
    -0.77
    POSITIVE LOGITS
    зопас
    0.65
    BagConstraints
    0.64
    ticulate
    0.59
    pagation
    0.58
    setOnItem
    0.58
     Chandler
    0.57
    acherous
    0.57
     []:
    0.57
    érience
    0.55
    irected
    0.55
    Activations Density 0.011%

    No Known Activations