© 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. 26398
    Prev
    Next
    INDEX
    Explanations

    terms related to compensation or compensatory actions

    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
     Lippincott
    -0.85
    TagHelpers
    -0.84
     McLeod
    -0.76
     Seele
    -0.67
    깥
    -0.67
    Unione
    -0.65
    VolleyError
    -0.63
    baye
    -0.62
    ungal
    -0.60
     Niz
    -0.60
    POSITIVE LOGITS
     compensation
    1.27
     Compensation
    1.21
    ENSATION
    1.20
    compensation
    1.19
    compens
    1.16
     compens
    1.16
    Compensation
    1.13
     Compens
    1.05
     compensate
    1.04
     compensating
    1.02
    Activations Density 0.005%

    No Known Activations