© 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. 23449
    Prev
    Next
    INDEX
    Explanations

    phrases related to current events and personal reflections

    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
    ظيم
    -0.59
     Inc
    -0.57
    lebnis
    -0.55
     calore
    -0.54
    etc
    -0.53
    org
    -0.53
     HttpResponse
    -0.53
     együtt
    -0.52
     etapas
    -0.51
    TargetApi
    -0.51
    POSITIVE LOGITS
     NSCoder
    0.85
     Wiktionnaire
    0.81
     AssemblyTitle
    0.76
    AutoField
    0.65
    concel
    0.65
    ANTLR
    0.64
    URLException
    0.64
    GOTREF
    0.62
     BoxDecoration
    0.61
    ="@+
    0.60
    Activations Density 0.016%

    No Known Activations