© 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. 9733
    Prev
    Next
    INDEX
    Explanations

    HTML class attributes and their values

    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
    LookAnd
    -0.71
     pinulongan
    -0.65
     jsPsych
    -0.64
    twimg
    -0.61
    HomeAsUpEnabled
    -0.58
    GraphicsUnit
    -0.57
    findpost
    -0.56
     tuyến
    -0.54
    MigrationBuilder
    -0.53
    Personensuche
    -0.52
    POSITIVE LOGITS
     ister
    0.55
    guien
    0.53
     hâte
    0.53
     resultCode
    0.53
     aikana
    0.52
     Valdés
    0.52
    uksessa
    0.52
     malheure
    0.52
     lateinit
    0.51
    theless
    0.50
    Activations Density 0.001%

    No Known Activations