© 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. 24797
    Prev
    Next
    INDEX
    Explanations

    the term "present" in various contexts, indicating it is focused on current or existing concepts related to inventions and methodologies

    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
     تانيه
    -0.91
    ("}\
    -0.77
    Obrázky
    -0.75
     ſche
    -0.73
     purpoſe
    -0.71
     jButton
    -0.69
     uſed
    -0.69
     Inſ
    -0.68
    OGND
    -0.68
     Inven
    -0.68
    POSITIVE LOGITS
    ˈ
    0.49
     on
    0.45
    έ
    0.45
    fillStyle
    0.43
    ниш
    0.42
    chave
    0.42
    sao
    0.42
    parseColor
    0.42
    ’
    0.42
    TacToe
    0.41
    Activations Density 0.003%

    No Known Activations