© 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. 10382
    Prev
    Next
    INDEX
    Explanations

    the word "somewhat" and its variants, indicating a degree of moderation or qualification

    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
    awtextra
    -0.76
    SuccessListener
    -0.73
     Tay
    -0.72
     "..\..\
    -0.70
    "><?=
    -0.68
    <?=
    -0.64
    /*!
    -0.63
    ).__
    -0.62
     fz
    -0.62
    といけない
    -0.62
    POSITIVE LOGITS
     quelcon
    0.82
    oporosis
    0.82
     giapp
    0.79
    GYPT
    0.77
    Ligações
    0.76
     adulte
    0.75
    varing
    0.75
     dépens
    0.74
     habet
    0.73
    antMatchers
    0.73
    Activations Density 0.003%

    No Known Activations