© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11685
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'b' or 'B' in various contexts, possibly indicating a focus on specific scientific notation or references

    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
    Negative Logits
    LookAnd
    -1.46
     Мексичка
    -1.30
     '\\;'
    -1.23
     autorytatywna
    -1.19
    rungsseite
    -1.15
    extAlignment
    -1.10
    ^(@)
    -1.09
     ProtoMessage
    -1.03
     calendriers
    -0.99
    DockStyle
    -0.97
    POSITIVE LOGITS
    is
    0.62
    ↵
    0.59
    /
    0.58
    i
    0.55
    0
    0.54
    N
    0.53
    ↵↵
    0.52
    2
    0.51
    ​
    0.50
    -
    0.50
    Activations Density 0.012%

    No Known Activations