© 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. 26725
    Prev
    Next
    INDEX
    Explanations

    technical specifications or identifiers in various contexts

    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
    InjectAttribute
    -0.81
    expandindo
    -0.74
     مشين
    -0.70
     <<<<<<<<<<<<<<
    -0.69
     الحره
    -0.67
     NSCoder
    -0.65
    granate
    -0.64
    reté
    -0.63
    NUMX
    -0.63
    Referencer
    -0.63
    POSITIVE LOGITS
     enfe
    0.45
     abbreviation
    0.45
     Jehová
    0.45
    $_['
    0.45
      
    0.44
     partea
    0.44
     stöd
    0.44
     chiedere
    0.44
     picioare
    0.44
     الحم
    0.43
    Activations Density 0.070%

    No Known Activations