© 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. 22249
    Prev
    Next
    INDEX
    Explanations

    phrases about explanations and details that enhance understanding of a topic

    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
    μέ
    -0.51
    ή
    -0.47
    pfe
    -0.47
    vors
    -0.46
     ط
    -0.44
     ص
    -0.44
    TA
    -0.44
    iores
    -0.42
     pavo
    -0.42
     how
    -0.42
    POSITIVE LOGITS
     defaultstate
    0.95
     CreateTagHelper
    0.91
     Lightboxes
    0.78
    abestanden
    0.76
    FieldBuilder
    0.76
     layui
    0.75
     getItemId
    0.75
     myſelf
    0.75
    PerformLayout
    0.75
     cellpadding
    0.74
    Activations Density 0.215%

    No Known Activations