© 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. 25768
    Prev
    Next
    INDEX
    Explanations

    the presence of prepositions in the text

    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
    thâu
    -0.80
    wahati
    -0.71
     Wicidata
    -0.70
     NSCoder
    -0.70
     referrerpolicy
    -0.68
     createSprite
    -0.68
     Roskov
    -0.68
    __':
    -0.67
    mybatisplus
    -0.66
     StatelessWidget
    -0.65
    POSITIVE LOGITS
     which
    0.65
    bootstrapcdn
    0.56
    which
    0.49
    PerformLayout
    0.49
     яко
    0.48
    ごめんなさい
    0.48
    lrrrr
    0.46
    которы
    0.46
     whereof
    0.45
     Wür
    0.45
    Activations Density 0.089%

    No Known Activations