© 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. 32044
    Prev
    Next
    INDEX
    Explanations

    phrases indicating prevalence and conditions related to populations or groups

    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
     tapi
    -0.50
    зумі
    -0.46
     parezca
    -0.42
     castello
    -0.42
     saiba
    -0.41
     but
    -0.40
    但
    -0.40
     Ofic
    -0.39
     belki
    -0.39
    AccessException
    -0.38
    POSITIVE LOGITS
     betweenstory
    0.93
    principalTable
    0.81
    bootstrapcdn
    0.79
    migrationBuilder
    0.78
     defaultstate
    0.77
     EconPapers
    0.76
     cherchés
    0.75
    MessageTagHelper
    0.74
     незавершена
    0.74
     onOptions
    0.69
    Activations Density 0.121%

    No Known Activations