© 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. 8439
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operations

    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
    GetAxis
    -0.78
     okuyayım
    -0.72
    protoimpl
    -0.69
     Giver
    -0.66
    iliger
    -0.65
    CrossRef
    -0.64
    Diwedd
    -0.63
    BufferException
    -0.62
    unknownFields
    -0.60
    chitz
    -0.60
    POSITIVE LOGITS
    overset
    1.70
     وتسجيلات
    0.99
    underset
    0.97
    esri
    0.72
     Osbourne
    0.68
     bestehen
    0.67
    */
    0.66
     Osborn
    0.66
    .'</
    0.66
    ."</
    0.66
    Activations Density 0.003%

    No Known Activations