© 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. 30818
    Prev
    Next
    INDEX
    Explanations

    image alternative text attributes

    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
    ✨:
    -0.71
    }');
    -0.68
     Napier
    -0.65
    RenderAtEndOf
    -0.65
    RegressionTest
    -0.64
    ↵↵
    -0.62
    -0.60
    ');?>
    -0.59
    +#+#
    -0.59
    `;
    -0.59
    POSITIVE LOGITS
     alt
    1.32
     Alt
    1.05
     ALT
    1.02
    alt
    0.95
    Alt
    0.93
     Altman
    0.92
     alts
    0.88
    ALT
    0.81
     Balt
    0.76
     OCS
    0.75
    Activations Density 0.003%

    No Known Activations