© 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. 18-RES-MATRYOSHKA-DC
    7. 646
    Prev
    Next
    INDEX
    Explanations

    the word "in" followed by the word "specific" or instances of legal writing or medical writing.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     للمعارف
    -0.71
     utafitiHapana
    -0.54
     '\\;'
    -0.52
     Roskov
    -0.51
    っこう
    -0.51
    \{\\
    -0.48
    httphttps
    -0.47
    zarchiwizowane
    -0.44
    zość
    -0.44
    Personensuche
    -0.43
    POSITIVE LOGITS
    第
    1.02
     #
    0.88
     Nummer
    0.80
     Item
    0.77
     Option
    0.76
     第
    0.76
     option
    0.76
     nummer
    0.75
     नंबर
    0.73
     №
    0.73
    Activations Density 3.092%

    No Known Activations