© 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. 5195
    Prev
    Next
    INDEX
    Explanations

    disturbing or unsettling content, especially those with dark, emotional, or distressing themes

    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
     Wiktionnaire
    -0.60
    dersfield
    -0.55
     pulso
    -0.55
     Commencez
    -0.55
    fromnode
    -0.55
     idiot
    -0.53
    negan
    -0.53
    ού
    -0.52
     innocence
    -0.51
    ReusableCell
    -0.51
    POSITIVE LOGITS
     disturbing
    1.59
     troubling
    1.52
     distressing
    1.41
     frightening
    1.40
     upsetting
    1.39
     unsettling
    1.33
     frustrating
    1.29
     alarming
    1.28
     depressing
    1.27
     discouraging
    1.26
    Activations Density 0.314%

    No Known Activations