© 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. 20415
    Prev
    Next
    INDEX
    Explanations

    instances of negation language

    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
    ing
    -0.73
     be
    -0.71
     able
    -0.66
    🏻
    -0.65
    NotBe
    -0.64
    Swift
    -0.63
     pince
    -0.62
    ientôt
    -0.61
    fromCharCode
    -0.61
    věř
    -0.61
    POSITIVE LOGITS
    Données
    0.87
     Moulton
    0.84
     SafeMath
    0.79
    Addo
    0.78
    KommentareTeilen
    0.76
     Völ
    0.76
    orses
    0.75
    Portail
    0.73
    dhury
    0.73
    UpInside
    0.73
    Activations Density 0.121%

    No Known Activations