© 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. 20750
    Prev
    Next
    INDEX
    Explanations

    references to logical reasoning or logic-related concepts

    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
    AccessorTable
    -0.90
    tvguidetime
    -0.90
    MigrationBuilder
    -0.83
    Personensuche
    -0.81
     ostavi
    -0.80
     épaules
    -0.79
    WriteTagHelper
    -0.76
     Barbour
    -0.76
     OkHttpClient
    -0.75
    fjspx
    -0.74
    POSITIVE LOGITS
     logic
    1.27
     Logic
    1.26
    LOGIC
    1.19
    logic
    1.18
     LOGIC
    1.17
    Logic
    1.09
    逻辑
    0.90
     log
    0.71
    1
    0.68
    0
    0.66
    Activations Density 0.003%

    No Known Activations