© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 19792
    Prev
    Next
    INDEX
    Explanations

    numerical data or lists of items

    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
    twimg
    -0.64
    UnsafeEnabled
    -0.61
    rinfo
    -0.59
     externi
    -0.57
    usermodel
    -0.56
     PeEnEo
    -0.55
    SharedCtor
    -0.54
    IBarButtonItem
    -0.52
    ыгана
    -0.52
    GeoNames
    -0.51
    POSITIVE LOGITS
    gof
    0.56
    !*\
    0.53
     Réponses
    0.53
    ="{{$
    0.50
    GOTREF
    0.49
    Dougall
    0.49
     nahilalakip
    0.49
    phazard
    0.47
    Zacks
    0.47
    oretical
    0.46
    Activations Density 0.007%

    No Known Activations