© 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. 12188
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize clarity and ease of understanding in explanations or analyses

    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
    HtmlAttribute
    -0.66
    VideoCapture
    -0.66
    URLException
    -0.64
    CloseOperation
    -0.61
    blurRadius
    -0.60
    DebuggerNonUser
    -0.58
    BoxShadow
    -0.57
    LinkId
    -0.57
    
    -0.57
    dflare
    -0.56
    POSITIVE LOGITS
    });*/
    0.53
    };*/
    0.52
    astéroïdes
    0.49
    ESSOR
    0.49
     }</
    0.48
     linearity
    0.47
    )')
    0.47
     üzerine
    0.46
    errHandler
    0.46
    ρασ
    0.46
    Activations Density 0.125%

    No Known Activations