© 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. 24-RES-MATRYOSHKA-DC
    7. 1241
    Prev
    Next
    INDEX
    Explanations

    the word "very" and adverbs modifying other words

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
     onCancelled
    -0.67
     betweenstory
    -0.66
     than
    -0.62
     decât
    -0.59
     geweldig
    -0.59
     esternos
    -0.58
    gäng
    -0.55
    それとも
    -0.55
     perfect
    -0.54
    printStackTrace
    -0.54
    POSITIVE LOGITS
    VERY
    0.73
    very
    0.73
    Very
    0.69
     Very
    0.66
     VERY
    0.63
     very
    0.55
    ///</
    0.52
     existence
    0.51
    few
    0.50
    thing
    0.50
    Activations Density 0.110%

    No Known Activations