© 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. 25294
    Prev
    Next
    INDEX
    Explanations

    mentions of conventions or related events

    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
     uParam
    -0.74
    ajaran
    -0.73
     Geor
    -0.69
    </em>
    -0.66
     bodyParser
    -0.66
    serialize
    -0.65
    STRO
    -0.65
     säs
    -0.64
     Kud
    -0.63
    Dorf
    -0.62
    POSITIVE LOGITS
    Convention
    1.52
     convention
    1.51
     Conventions
    1.48
     Convention
    1.45
     conventions
    1.41
    convention
    1.38
    Conven
    1.19
     Conven
    1.09
    conven
    1.06
    StoryboardSegue
    0.96
    Activations Density 0.003%

    No Known Activations