© 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. 3587
    Prev
    Next
    INDEX
    Explanations

    references to mental health problems

    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
     brain
    -0.98
     brains
    -0.98
    brain
    -0.91
     Brain
    -0.87
    Brain
    -0.85
    Brains
    -0.82
     Brains
    -0.80
    brains
    -0.78
     referenties
    -0.75
     BRAIN
    -0.74
    POSITIVE LOGITS
     mental
    2.80
     Mental
    2.69
    Mental
    2.59
    mental
    2.42
     MENTAL
    2.33
     mentally
    1.94
     mentale
    1.80
     mentales
    1.55
     Ment
    1.09
    Ment
    0.91
    Activations Density 0.007%

    No Known Activations