© 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. 10616
    Prev
    Next
    INDEX
    Explanations

    the word "comprehensive" and its variations, indicating a focus on thoroughness and completeness

    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
     OMITBAD
    -0.87
    pyplot
    -0.79
     AsyncTask
    -0.76
     getItemId
    -0.73
    Hozzáférés
    -0.73
     LoginComponent
    -0.73
     Kik
    -0.71
    InjectMocks
    -0.71
    saraba
    -0.70
    CodedInputStream
    -0.67
    POSITIVE LOGITS
    prehensive
    1.13
     Comprehensive
    1.05
     comprehensive
    1.04
    Comprehensive
    1.04
    comprehensive
    1.02
    rehensive
    0.90
     umfass
    0.81
     comprehen
    0.77
    wchar
    0.77
     comprehensively
    0.74
    Activations Density 0.004%

    No Known Activations