© 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. 12627
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives and terms indicating increase or decrease in quantity

    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
    jant
    -0.60
     but
    -0.54
     or
    -0.51
     AssemblyTitle
    -0.48
     i
    -0.47
     TType
    -0.47
     he
    -0.46
     some
    -0.46
    iacute
    -0.44
    nice
    -0.44
    POSITIVE LOGITS
     ſeveral
    0.91
     houſe
    0.90
     Diſ
    0.88
     Efq
    0.85
     ſche
    0.84
     Conſ
    0.83
    protoimpl
    0.82
     poffe
    0.82
     ſtate
    0.82
     ſame
    0.81
    Activations Density 0.012%

    No Known Activations