© 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. 26679
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly negative numbers and their representations

    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
    发表于
    -0.67
     gib
    -0.62
    jooq
    -0.59
     Insee
    -0.59
    GRANTED
    -0.55
     wel
    -0.54
    uxxxx
    -0.54
    RESUMO
    -0.53
    ########.
    -0.53
     oprot
    -0.53
    POSITIVE LOGITS
     myſelf
    1.16
     themſelves
    0.98
     pleaſure
    0.96
     itſelf
    0.91
     Houſe
    0.88
     fevere
    0.85
     purpoſe
    0.85
     Monfieur
    0.85
     Efq
    0.84
     Majefty
    0.83
    Activations Density 0.010%

    No Known Activations