© 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. 14275
    Prev
    Next
    INDEX
    Explanations

    phrases related to the limitations and implications of legal or procedural concepts

    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
    AndEndTag
    -0.71
     pinulongan
    -0.50
    SuccessListener
    -0.48
     informée
    -0.48
    burgo
    -0.47
    modelBuilder
    -0.47
    luka
    -0.47
    URLException
    -0.46
    ']):
    -0.44
    stylers
    -0.44
    POSITIVE LOGITS
    Hentet
    0.66
    :✨
    0.63
    akterysty
    0.59
    SharedCtor
    0.57
    Cyfeiriadau
    0.56
    ellón
    0.55
     chi̍t
    0.52
    BeginInit
    0.52
     المعيارى
    0.51
     Reverso
    0.51
    Activations Density 0.366%

    No Known Activations