© 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. 26465
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to scientific papers

    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
    цездатний
    -0.94
     gradova
    -0.68
    ⓧ
    -0.65
    EndGlobalSection
    -0.65
     EnglishChoose
    -0.62
    BeginContext
    -0.61
    पया
    -0.60
    ArgsConstructor
    -0.60
     الحره
    -0.59
     pinulongan
    -0.57
    POSITIVE LOGITS
     {}'.
    0.62
     {}".
    0.57
    rungsseite
    0.55
    nastics
    0.52
    agua
    0.50
    grounds
    0.49
     pii
    0.49
    sociation
    0.48
    freiheit
    0.48
    UnusedPrivate
    0.48
    Activations Density 0.020%

    No Known Activations