© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 24236
    Prev
    Next
    INDEX
    Explanations

    CSS class selectors and their properties

    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
     universitarios
    -0.60
     sahiptir
    -0.58
     comunale
    -0.54
     yoktur
    -0.53
     universitario
    -0.51
     chegada
    -0.49
     péri
    -0.48
     Evers
    -0.48
     scolas
    -0.47
     esportivo
    -0.47
    POSITIVE LOGITS
    protoimpl
    0.90
    posedge
    0.88
    ContentAsync
    0.79
    ConstraintMaker
    0.77
    writerow
    0.76
     ***!
    0.76
    Дереккөздер
    0.74
    WireFormatLite
    0.72
    cleros
    0.71
    WriteTagHelper
    0.71
    Activations Density 0.001%

    No Known Activations