© 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. 14474
    Prev
    Next
    INDEX
    Explanations

    instances of the word "legitimate" relating to various contexts

    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
     Brentford
    -0.75
     Trento
    -0.72
    
    -0.70
    ❦
    -0.68
     Insect
    -0.68
     Annan
    -0.67
     Sulawesi
    -0.66
     Kauai
    -0.66
     beeswax
    -0.66
    WebElementEntity
    -0.65
    POSITIVE LOGITS
    itimate
    1.52
     legitimate
    1.12
     legiti
    0.96
     illegitimate
    0.92
     legit
    0.90
     legitimacy
    0.90
     legitimately
    0.89
     légitime
    0.88
     légiti
    0.85
    itim
    0.83
    Activations Density 0.006%

    No Known Activations