© 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. 26064
    Prev
    Next
    INDEX
    Explanations

    keys or identifiers in structured data formats

    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
     pinulongan
    -0.88
    makeText
    -0.82
     للمعارف
    -0.79
     وتسجيلات
    -0.75
    PyExc
    -0.72
    bootstrapcdn
    -0.71
    TagHelper
    -0.70
     opérés
    -0.68
    IVEREF
    -0.66
     ComVisible
    -0.65
    POSITIVE LOGITS
    setVerticalGroup
    0.54
     "..\..\
    0.53
    phants
    0.52
    мум
    0.52
     propOrder
    0.51
    ouple
    0.50
    mount
    0.50
    onames
    0.50
     zasady
    0.50
    越好
    0.49
    Activations Density 0.001%

    No Known Activations