© 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. 12-RES-MATRYOSHKA-DC
    7. 23743
    Prev
    Next
    INDEX
    Explanations

    terms related to healing and recovery

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    WebElementEntity
    -0.76
     autorytatywna
    -0.74
     pinulongan
    -0.73
     Bertrand
    -0.72
    Bertrand
    -0.72
    +#+
    -0.68
     propOrder
    -0.67
     nonatomic
    -0.67
    tadır
    -0.66
    MigrationBuilder
    -0.66
    POSITIVE LOGITS
     Healing
    1.60
     healing
    1.55
    Healing
    1.55
     healed
    1.51
     heal
    1.49
    healing
    1.48
     heals
    1.41
    Heal
    1.38
     Heal
    1.37
    heal
    1.29
    Activations Density 0.003%

    No Known Activations