© 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. 12764
    Prev
    Next
    INDEX
    Explanations

    key concepts related to organization and collaboration in projects or discussions

    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
    脚注の使い方
    -0.54
    chette
    -0.48
     vandal
    -0.47
     विश्वसनीयता
    -0.47
    lors
    -0.47
    lné
    -0.46
    PasswordField
    -0.46
    δρ
    -0.46
    expert
    -0.45
    medriver
    -0.45
    POSITIVE LOGITS
     organizer
    0.70
     organizing
    0.69
     organizador
    0.68
     насељу
    0.68
     Organizer
    0.67
     disambiguazione
    0.66
     Organiser
    0.66
     organiser
    0.65
     organizers
    0.64
    ValueGenerated
    0.62
    Activations Density 0.398%

    No Known Activations