© 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. 14705
    Prev
    Next
    INDEX
    Explanations

    URLs and web resource references

    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
     mergeFrom
    -0.54
    parsedMessage
    -0.54
    toContain
    -0.51
     lắm
    -0.50
     réussite
    -0.49
    complexType
    -0.48
    transQ
    -0.48
     sociétés
    -0.48
    DropTable
    -0.47
    omburg
    -0.46
    POSITIVE LOGITS
    
    0.81
    ValueStyle
    0.78
    Hozzáférés
    0.76
     referrerpolicy
    0.75
     BoxFit
    0.73
     springfox
    0.69
    URLException
    0.68
     FetchType
    0.67
     CURIAM
    0.67
    migrationBuilder
    0.64
    Activations Density 0.014%

    No Known Activations