© 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. 30391
    Prev
    Next
    INDEX
    Explanations

    references to statistical concepts and unknown parameters

    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
     []:
    -0.57
    upassen
    -0.57
    Véxase
    -0.56
    NOPQRST
    -0.56
    AccessorTable
    -0.55
    ButterKnife
    -0.54
    )':
    -0.54
    ,:);
    -0.53
    akir
    -0.52
    новниш
    -0.51
    POSITIVE LOGITS
    GeneratedCode
    0.56
    Rüyada
    0.55
    nezeu
    0.51
     Económica
    0.51
    jenner
    0.50
    سرائيل
    0.48
    <!--[
    0.47
     olet
    0.47
    Taylor
    0.47
     samarbeid
    0.47
    Activations Density 0.111%

    No Known Activations