© 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. 14743
    Prev
    Next
    INDEX
    Explanations

    references to applicants and buyers in the context of financial or legal documents

    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
    es
    -0.83
    esine
    -0.63
     Tor
    -0.61
    ES
    -0.61
    Kaynakça
    -0.59
    2
    -0.58
    djangoproject
    -0.58
    ed
    -0.57
    Tor
    -0.57
     Mil
    -0.57
    POSITIVE LOGITS
     Applicants
    1.14
    applicant
    1.12
    Applicant
    1.08
     Monfieur
    1.08
    ^(@)
    1.07
     Applicant
    1.06
     ―――――
    1.04
    Applicants
    1.00
     applicants
    1.00
     applicant
    0.98
    Activations Density 0.005%

    No Known Activations