© 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. 10420
    Prev
    Next
    INDEX
    Explanations

    phrases and structures indicating data transmission to a recipient

    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
    RectangleBorder
    -0.87
    EndInit
    -0.82
    UserScript
    -0.77
    HostException
    -0.76
     tartalomajánló
    -0.75
    AnchorStyles
    -0.72
    })();
    -0.72
     pinulongan
    -0.70
    EndContext
    -0.69
    ngrx
    -0.67
    POSITIVE LOGITS
     truyền
    0.62
     Sent
    0.54
    Сле
    0.52
     Pall
    0.52
    leon
    0.52
    چال
    0.51
     contrari
    0.51
    ۪
    0.51
     saites
    0.50
     there
    0.50
    Activations Density 0.048%

    No Known Activations