© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17574
    Prev
    Next
    INDEX
    Explanations

    the term "Ltd," indicating associations with limited companies

    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
    й
    -0.80
    crip
    -0.62
    inc
    -0.60
    ation
    -0.60
    いな
    -0.59
    er
    -0.58
    ン
    -0.58
    an
    -0.58
    м
    -0.58
     mas
    -0.57
    POSITIVE LOGITS
     Ltd
    1.19
    ]--;
    1.06
    Ltd
    1.04
    )_/¯
    1.00
     tartalomajánló
    0.97
    "}"
    0.96
     ltd
    0.93
     виправивши
    0.93
    LTD
    0.93
     LTD
    0.91
    Activations Density 0.006%

    No Known Activations