© 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. 22-RES-MATRYOSHKA-DC
    7. 1496
    Prev
    Next
    INDEX
    Explanations

    punctuation marks surrounded by other words along with the relative importance or agreement by the author

    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.22.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.22.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
    她們
    -0.67
     &=&
    -0.63
     fallu
    -0.63
     которое
    -0.60
    &=&\
    -0.59
    她们
    -0.59
     करती
    -0.57
    &=&
    -0.55
     Оно
    -0.52
    ')->
    -0.51
    POSITIVE LOGITS
     his
    3.23
     he
    3.22
     him
    2.91
    彼は
    2.61
     himself
    2.45
    his
    2.44
    彼の
    2.36
    彼が
    2.31
     egli
    2.23
     그는
    2.22
    Activations Density 6.260%

    No Known Activations