© 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. 18896
    Prev
    Next
    INDEX
    Explanations

    phrases indicating agreements or offers

    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
     مشين
    -0.69
    Vivi
    -0.59
     rejection
    -0.57
     Reject
    -0.56
     acknowledge
    -0.55
    %@",
    -0.55
    Amicalement
    -0.55
    pology
    -0.53
    (%)
    -0.53
     Chasse
    -0.53
    POSITIVE LOGITS
     câte
    0.68
    ForValue
    0.66
    CompleteListener
    0.66
     Fuerzas
    0.65
     feroit
    0.65
    openqa
    0.63
    SBATCH
    0.63
    WebMethod
    0.60
     kohta
    0.60
    pushFollow
    0.59
    Activations Density 0.015%

    No Known Activations