© 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. 11569
    Prev
    Next
    INDEX
    Explanations

    instances of the word "literally" or related forms

    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
    rouch
    -0.60
     entanto
    -0.60
     Harden
    -0.54
     lauk
    -0.54
     Mayfield
    -0.54
     squash
    -0.53
     Durant
    -0.53
    Romain
    -0.53
     sínt
    -0.52
    peq
    -0.52
    POSITIVE LOGITS
     literally
    1.33
    literally
    1.25
     Literally
    1.21
    Literally
    1.20
     literal
    1.17
     literalmente
    1.12
    LITERAL
    0.97
    literal
    0.97
     Literal
    0.95
    rrggbb
    0.91
    Activations Density 0.004%

    No Known Activations