© 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. 32461
    Prev
    Next
    INDEX
    Explanations

    references to goals and objectives

    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
     intended
    -0.80
    intended
    -0.77
     Intended
    -0.72
    ly
    -0.63
    Intended
    -0.63
     It
    -0.60
    ceum
    -0.57
    Esprit
    -0.57
     I
    -0.55
     tangan
    -0.55
    POSITIVE LOGITS
     GOAL
    1.28
     Goals
    1.26
    GOAL
    1.23
     GOALS
    1.20
    goals
    1.17
     Goal
    1.15
     poffe
    1.14
     Efq
    1.14
    Goals
    1.12
     goals
    1.10
    Activations Density 0.011%

    No Known Activations