© 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. 10125
    Prev
    Next
    INDEX
    Explanations

    references to scientific articles or documents, especially those related to research metrics such as DOI numbers

    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
     tartalomajánló
    -0.79
    AnchorStyles
    -0.73
     Doi
    -0.66
     unknownFields
    -0.65
    vastava
    -0.64
     Newberry
    -0.61
    SequentialGroup
    -0.60
     Aoki
    -0.59
     Mackey
    -0.59
     Quay
    -0.59
    POSITIVE LOGITS
    Izvori
    0.63
    ForType
    0.61
    הערות
    0.59
    ereo
    0.56
    oa̍t
    0.56
    "]));
    0.53
     utafitiHapana
    0.52
     story
    0.52
    gwt
    0.52
    ViewFeatures
    0.51
    Activations Density 0.004%

    No Known Activations