© 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. 272
    Prev
    Next
    INDEX
    Explanations

    instances of words that start with the prefix "sub-", and a few prefixes consisting of two letters

    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
     ainfi
    -0.90
     Theſe
    -0.90
     Efq
    -0.90
    lijck
    -0.83
     ſhould
    -0.82
     Jefus
    -0.77
     itſelf
    -0.77
     becauſe
    -0.76
     ſhall
    -0.75
     myſelf
    -0.74
    POSITIVE LOGITS
    -
    0.92
     inter
    0.79
     pre
    0.75
    Pre
    0.69
     sub
    0.69
     re
    0.68
    pre
    0.68
    Re
    0.66
     trans
    0.65
     dé
    0.63
    Activations Density 1.289%

    No Known Activations