© 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. 22665
    Prev
    Next
    INDEX
    Explanations

    instances of misconduct or improper behavior in a legal context

    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
    ResumeLayout
    -0.91
     Varela
    -0.85
     المعيارى
    -0.84
    IntoConstraints
    -0.81
    MLLoader
    -0.80
    AddTagHelper
    -0.79
    makeConstraints
    -0.77
     AssemblyCompany
    -0.76
    umbersome
    -0.76
     localObject
    -0.74
    POSITIVE LOGITS
     misconduct
    0.57
     play
    0.44
    PhysRev
    0.43
    zeigen
    0.41
    Ok
    0.41
     sẻ
    0.39
    anto
    0.39
     wij
    0.38
    liwości
    0.38
    PhysRevLett
    0.38
    Activations Density 0.009%

    No Known Activations