© 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. 31339
    Prev
    Next
    INDEX
    Explanations

    quantitative data or statistical values related to experiments or studies

    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
    .*")]
    -0.78
    󠁢
    -0.55
    abstractmethod
    -0.54
     abſ
    -0.50
    ✨:
    -0.50
     createSlice
    -0.48
     infarction
    -0.47
     tanı
    -0.47
     obſ
    -0.47
     anſ
    -0.46
    POSITIVE LOGITS
     unknownFields
    0.65
    новништво
    0.61
    didReceive
    0.59
    uele
    0.59
    nière
    0.59
    ("}\
    0.58
    nyv
    0.58
    prits
    0.57
    AccessorTable
    0.57
    EDUC
    0.55
    Activations Density 0.006%

    No Known Activations