© 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. 28451
    Prev
    Next
    INDEX
    Explanations

    words related to permissions or allowing actions

    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
    findpost
    -0.97
    ChildScrollView
    -0.93
    Weblinks
    -0.87
    __*/
    -0.86
     }^{[
    -0.82
    NameInMap
    -0.81
    DotNetBar
    -0.80
    abestanden
    -0.79
     defaultstate
    -0.79
    HasMaxLength
    -0.78
    POSITIVE LOGITS
     Permit
    0.91
    Permit
    0.86
     permits
    0.82
     permit
    0.80
     Permits
    0.80
     PERMIT
    0.75
    permitted
    0.72
     permitted
    0.69
     Pem
    0.69
    permit
    0.69
    Activations Density 0.008%

    No Known Activations