© 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. 18835
    Prev
    Next
    INDEX
    Explanations

    forms and structures associated with data or input forms in a web application context

    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
    Personendaten
    -0.90
    saraba
    -0.81
     Himo
    -0.76
     HasFactory
    -0.76
    WriteBarrier
    -0.74
     ModelExpression
    -0.74
    ResponseWriter
    -0.73
    Jeografia
    -0.73
     समीक्षक
    -0.73
     AssemblyVersion
    -0.71
    POSITIVE LOGITS
     Sch
    0.56
     Wend
    0.55
    Sch
    0.55
    Tram
    0.55
    sch
    0.53
     sna
    0.51
    osaurus
    0.50
     détaillés
    0.49
    roned
    0.48
    Amb
    0.48
    Activations Density 0.010%

    No Known Activations