© 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. 22676
    Prev
    Next
    INDEX
    Explanations

    the word "rather" in various contexts

    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
    Vij
    -0.75
    paravant
    -0.74
     instead
    -0.71
     Instead
    -0.71
    ToBounds
    -0.68
    Instead
    -0.66
    tisol
    -0.65
    feest
    -0.65
     Vij
    -0.64
     уч
    -0.63
    POSITIVE LOGITS
     ***/
    0.92
    er
    0.92
     MPR
    0.82
    $>$
    0.81
     pager
    0.80
     Bemer
    0.77
    erer
    0.76
     LTS
    0.76
    Rau
    0.75
     Bourne
    0.75
    Activations Density 0.015%

    No Known Activations