© 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. 3663
    Prev
    Next
    INDEX
    Explanations

    technical specifications and dimensions related to data representations or figures

    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
     GenerationType
    -0.62
     الرياضيه
    -0.61
    tvguidetime
    -0.59
     كومونز
    -0.58
    følgelig
    -0.58
     AssemblyTitle
    -0.57
     eds
    -0.53
     CWE
    -0.52
    XtraReports
    -0.52
    PIR
    -0.52
    POSITIVE LOGITS
     île
    0.50
     époque
    0.50
     naturali
    0.50
    सन्दर्भ
    0.49
     suh
    0.48
    icidio
    0.48
     Mémoires
    0.48
    enem
    0.47
    toso
    0.47
     fusca
    0.47
    Activations Density 0.038%

    No Known Activations