© 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. 22-RES-MATRYOSHKA-DC
    7. 144
    Prev
    Next
    INDEX
    Explanations

    words related to difficult emotional experiences

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IIRC
    -0.84
     overkill
    -0.78
     dodgy
    -0.72
     omin
    -0.68
     complained
    -0.68
     iirc
    -0.67
     suspiciously
    -0.67
     disgruntled
    -0.66
    handy
    -0.66
     annoyed
    -0.66
    POSITIVE LOGITS
     empowering
    0.88
     empower
    0.84
     empowers
    0.82
     nurturing
    0.79
     enriching
    0.78
     deeply
    0.77
     empowered
    0.77
     profondément
    0.77
     enrich
    0.76
     healing
    0.74
    Activations Density 5.194%

    No Known Activations