© 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. 31832
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "essential"

    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
    VersionUID
    -0.99
    httphttps
    -0.98
    Pfalz
    -0.95
    digarh
    -0.94
    DockStyle
    -0.91
    VIAF
    -0.88
    <!--[
    -0.87
     Walkover
    -0.87
    mediately
    -0.86
    getKeyCode
    -0.86
    POSITIVE LOGITS
     Essentials
    1.02
    Ess
    1.02
     Ess
    0.98
    Essen
    0.98
     Essen
    0.91
     essenziale
    0.90
     ESS
    0.86
    ESS
    0.82
     esenciales
    0.82
    Essentials
    0.80
    Activations Density 0.016%

    No Known Activations