© 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. 10065
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or labels within technical documents

    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
    INGHAM
    -0.52
    </h5>
    -0.44
    </s>
    -0.44
    eche
    -0.44
    paged
    -0.43
    IOUS
    -0.43
    ridged
    -0.43
    ,:]
    -0.43
    ymal
    -0.42
     Schach
    -0.42
    POSITIVE LOGITS
     ***!
    0.84
    InjectAttribute
    0.82
     Infórmanos
    0.79
    adaptiveStyles
    0.75
    RegressionTest
    0.71
    UnsafeEnabled
    0.71
     wikipagina
    0.69
    EDEFAULT
    0.69
     للاسماء
    0.67
    withIdentifier
    0.67
    Activations Density 0.237%

    No Known Activations