© 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. 4719
    Prev
    Next
    INDEX
    Explanations

    references to acts of destruction

    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
     injury
    -0.66
     olympiques
    -0.63
     Injuries
    -0.62
     Injury
    -0.62
    ליה
    -0.62
     thanksgiving
    -0.61
    jspx
    -0.60
     hypoxia
    -0.60
     injuries
    -0.59
     Schnee
    -0.59
    POSITIVE LOGITS
     destroy
    2.95
     destruction
    2.81
     Destroy
    2.73
     destroyed
    2.72
     Destruction
    2.67
     destroying
    2.64
     destroys
    2.59
    destroy
    2.45
    destruction
    2.39
    destroyed
    2.36
    Activations Density 0.058%

    No Known Activations