© 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. 23779
    Prev
    Next
    INDEX
    Explanations

    ingredients and instructions related to cooking or baking activities

    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
    AnimationsModule
    -0.51
    ApiModelProperty
    -0.51
     Dore
    -0.47
    Scaler
    -0.46
     Watch
    -0.45
     Caron
    -0.45
    rawtypes
    -0.44
    Facet
    -0.44
     Glass
    -0.44
    </table>
    -0.43
    POSITIVE LOGITS
     dough
    1.07
    Dough
    1.01
     Dough
    0.96
     kne
    0.89
    ViewImports
    0.84
    gonic
    0.84
     typelib
    0.81
    dough
    0.77
    ArgsConstructor
    0.76
    躇
    0.75
    Activations Density 0.009%

    No Known Activations