© 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. 22941
    Prev
    Next
    INDEX
    Explanations

    numerical representations or data related to mathematical 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
    ########.
    -0.68
     McClure
    -0.68
    }>;
    -0.65
    Frosty
    -0.65
    oirs
    -0.62
    ORIAL
    -0.61
    CopyWith
    -0.60
     Artur
    -0.60
    pto
    -0.59
    ();*/
    -0.59
    POSITIVE LOGITS
    AccessorTable
    0.79
     Wicidata
    0.68
    Eres
    0.68
     Unidas
    0.66
    :✨
    0.64
     Réponses
    0.64
     Lég
    0.57
    Datuak
    0.57
    MessageOf
    0.57
    elemField
    0.54
    Activations Density 0.113%

    No Known Activations