© 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. 13641
    Prev
    Next
    INDEX
    Explanations

    negative numerical values or expressions

    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
     Tait
    -0.64
    POSIT
    -0.53
    ftagPool
    -0.50
    락
    -0.50
    zusch
    -0.49
     válido
    -0.49
    Davide
    -0.49
     Waite
    -0.48
    нович
    -0.47
     Ausgaben
    -0.47
    POSITIVE LOGITS
    WSGI
    0.74
     Houſe
    0.70
    存于互联网档案馆
    0.69
     ویکی‌پدیای
    0.68
     defaultstate
    0.67
     '\\;'
    0.65
     arşivlendi
    0.63
     EconPapers
    0.63
    ]")]
    0.63
     Uncategorized
    0.63
    Activations Density 0.026%

    No Known Activations