© 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. 31012
    Prev
    Next
    INDEX
    Explanations

    instances of numerical and symbolic sequences

    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
     Мексичка
    -0.71
     فريبيس
    -0.70
    MigrationBuilder
    -0.69
    migrationBuilder
    -0.68
    enumi
    -0.64
     okuyayım
    -0.63
    assertRaises
    -0.60
    cookieParser
    -0.60
    ouille
    -0.59
    IntoConstraints
    -0.58
    POSITIVE LOGITS
    thâu
    0.52
    DoubleQuotes
    0.51
     Praw
    0.48
     piłkarz
    0.47
    Cadastrar
    0.47
     cerrados
    0.47
    ▲
    0.47
    ⓧ
    0.47
    GIVEREF
    0.47
    מיד
    0.46
    Activations Density 0.019%

    No Known Activations