© 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. 24910
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to informed consent and information transparency

    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
    EOUS
    -0.70
    lerc
    -0.66
    locene
    -0.66
     Gries
    -0.65
    lidene
    -0.64
    TryGetValue
    -0.64
     fotografico
    -0.62
     gars
    -0.62
     Everest
    -0.61
    vieve
    -0.61
    POSITIVE LOGITS
     Informed
    1.23
    Informed
    1.11
     Inform
    1.08
    Inform
    1.07
     INFORM
    1.05
     informed
    1.03
    informed
    1.02
     informs
    1.01
     informing
    0.99
    inform
    0.98
    Activations Density 0.012%

    No Known Activations