© 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. 2223
    Prev
    Next
    INDEX
    Explanations

    strings related to the term "the" in variable references

    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
     are
    -0.56
     were
    -0.54
     should
    -0.52
     is
    -0.51
    '
    -0.50
    .
    -0.50
    넷
    -0.48
    ;
    -0.46
     Gott
    -0.44
     am
    -0.43
    POSITIVE LOGITS
     disambiguazione
    1.17
    tvguidetime
    1.05
    
    1.02
     Савезне
    0.91
     خارجية
    0.90
     Wicidata
    0.88
    Revenir
    0.88
     nahilalakip
    0.88
    OGND
    0.87
     insuffisamment
    0.86
    Activations Density 0.789%

    No Known Activations