© 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. 18-RES-MATRYOSHKA-DC
    7. 39
    Prev
    Next
    INDEX
    Explanations

    the word "the", but also seems to activate for a few other random words

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     propOrder
    -0.81
     Fascism
    -0.81
     Euripides
    -0.80
     Assyrian
    -0.77
     Huguen
    -0.75
     Chaldean
    -0.75
     Pilate
    -0.73
     ciascuno
    -0.72
     Mahomet
    -0.72
     démocr
    -0.72
    POSITIVE LOGITS
     same
    1.57
     entire
    1.34
     latter
    1.25
     rest
    1.16
     most
    1.11
     final
    1.09
     whole
    1.09
     usual
    1.04
     last
    1.02
     vast
    1.02
    Activations Density 4.472%

    No Known Activations