© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17419
    Prev
    Next
    INDEX
    Explanations

    results indicating the validity and robustness of experimental findings

    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
    rrggbb
    -0.62
    tvguidetime
    -0.58
    lapsingToolbar
    -0.54
     légende
    -0.52
    Batis
    -0.50
    aarrggbb
    -0.49
     étoit
    -0.49
     eût
    -0.48
     fût
    -0.48
     colonnes
    -0.48
    POSITIVE LOGITS
    IndentedString
    0.84
    protoimpl
    0.61
     mergeFrom
    0.56
    sego
    0.53
    withIdentifier
    0.52
    IUrlHelper
    0.52
     BoxDecoration
    0.50
    Obrázky
    0.49
    maps
    0.49
    REFERRED
    0.49
    Activations Density 0.175%

    No Known Activations