© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 6845
    Prev
    Next
    INDEX
    Explanations

    file paths and directory structures

    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
    Negative Logits
    neté
    -0.54
     muualla
    -0.53
    ieR
    -0.52
     незавершена
    -0.51
    〗
    -0.49
    WireFormat
    -0.48
     الاطلاع
    -0.47
     Borg
    -0.47
    ционер
    -0.47
    acá
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.76
    +#+#
    0.69
    CodedInputStream
    0.66
     createState
    0.63
    SharedCtor
    0.63
    ViewFeatures
    0.59
    Parcelize
    0.57
    InSection
    0.57
    posedge
    0.56
     Cancelar
    0.56
    Activations Density 0.321%

    No Known Activations