© 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. 8830
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to mathematical notation and functions

    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
    [
    -0.65
    V
    -0.60
     sp
    -0.58
    t
    -0.57
    w
    -0.57
    bit
    -0.57
    m
    -0.57
    weren
    -0.56
    n
    -0.56
    et
    -0.56
    POSITIVE LOGITS
     يتيمه
    1.02
    bigg
    1.00
    AndEndTag
    0.97
    ^(@)
    0.96
    culoskeletal
    0.94
    {}".
    0.94
     doubtnut
    0.93
    BibitemShut
    0.90
    '")
    0.90
     дописавши
    0.86
    Activations Density 0.013%

    No Known Activations