© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 32607
    Prev
    Next
    INDEX
    Explanations

    concepts related to various forms or qualities of "ness"

    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
    Negative Logits
    uley
    -0.89
    jectable
    -0.81
     cry
    -0.79
    unay
    -0.77
    Locality
    -0.75
     Coyle
    -0.74
    لكتر
    -0.73
     endwhile
    -0.72
    Portale
    -0.72
     Shreve
    -0.72
    POSITIVE LOGITS
    ness
    1.48
    iness
    1.22
    NESS
    1.09
    eness
    0.90
    nesses
    0.88
     ness
    0.88
    Ness
    0.86
     Moos
    0.85
    es
    0.85
    expandindo
    0.81
    Activations Density 0.042%

    No Known Activations