© 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. 17763
    Prev
    Next
    INDEX
    Explanations

    structural elements and parameters in code or mathematical expressions

    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
    Viited
    -0.74
    WebVitals
    -0.69
    BASEPATH
    -0.68
     vPvB
    -0.68
     يتيمه
    -0.68
     وتسجيلات
    -0.68
     otomatig
    -0.66
    RUnlock
    -0.63
    Дереккөздер
    -0.63
     resourceCulture
    -0.62
    POSITIVE LOGITS
    quet
    0.43
    коном
    0.42
     setName
    0.41
    eldo
    0.41
    indu
    0.40
    Caracter
    0.40
    utado
    0.40
    kwij
    0.40
    gele
    0.40
    spiegel
    0.40
    Activations Density 0.266%

    No Known Activations