© 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. 28633
    Prev
    Next
    INDEX
    Explanations

    patterns of repeated phrases or segments typically used as placeholders or in coding contexts

    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
     defaultdict
    -0.89
     Plum
    -0.86
     Planck
    -0.85
     Schindler
    -0.85
    Plum
    -0.84
     FetchType
    -0.81
    JNIEnv
    -0.81
    PIECE
    -0.81
     gắng
    -0.80
    Sedan
    -0.80
    POSITIVE LOGITS
     Bla
    1.55
    bla
    1.54
     bla
    1.52
    Bla
    1.46
     BLA
    1.31
     Blair
    1.25
    BLA
    1.25
    Blair
    1.10
     Blazers
    1.03
     Blak
    0.98
    Activations Density 0.006%

    No Known Activations