© 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. 18578
    Prev
    Next
    INDEX
    Explanations

    terms that indicate importance or relevance in scientific 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
     vocale
    -0.54
    Delaware
    -0.54
    ↵↵
    -0.53
    cagon
    -0.51
    atorship
    -0.51
    TAINMENT
    -0.51
     douleur
    -0.50
     proposons
    -0.50
    stdc
    -0.50
     victime
    -0.49
    POSITIVE LOGITS
     nakalista
    0.87
    DebuggerNonUser
    0.75
     BoxFit
    0.73
    writeField
    0.71
     Савезне
    0.71
    !")
    0.66
    Jereo
    0.64
     متعلقه
    0.63
    期刊论文
    0.63
     Италијани
    0.61
    Activations Density 0.032%

    No Known Activations