© 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. 22189
    Prev
    Next
    INDEX
    Explanations

    numerical values and quantities within the text

    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
    SharedCtor
    -0.68
     étoit
    -0.67
    цездатний
    -0.64
     Biôgrafia
    -0.63
     AssemblyCulture
    -0.59
     NORD
    -0.59
    Према
    -0.58
     Masala
    -0.58
     étoient
    -0.58
     henvisninger
    -0.57
    POSITIVE LOGITS
    slam
    0.48
    CloseOperation
    0.47
    HasColumnType
    0.46
    bní
    0.46
    ExecuteReader
    0.45
    MemoryWarning
    0.43
    FailureListener
    0.43
    Datuak
    0.41
    BindingResult
    0.41
    DataAnnotations
    0.40
    Activations Density 0.002%

    No Known Activations