© 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. 30726
    Prev
    Next
    INDEX
    Explanations

    references to appointments or the act of appointing

    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
     lugs
    -0.89
     studs
    -0.76
    llog
    -0.75
     jurídica
    -0.73
    empereur
    -0.72
     giuri
    -0.71
     Waray
    -0.69
    enciaga
    -0.69
    httphttps
    -0.69
     StringVar
    -0.69
    POSITIVE LOGITS
     Appointments
    1.34
     appointment
    1.29
     appointments
    1.26
    Appointment
    1.25
     Appointment
    1.23
     APPOINT
    1.21
     appoint
    1.19
     appointing
    1.13
    Appointments
    1.13
    appoint
    1.10
    Activations Density 0.008%

    No Known Activations