© 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. 22-RES-MATRYOSHKA-DC
    7. 1967
    Prev
    Next
    INDEX
    Explanations

    the verb "make" followed by a determiner and an object

    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.22.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.22.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
    contentLoaded
    -0.69
    PreferredItem
    -0.68
    олові
    -0.68
     <<<<<<<<<<<<<<
    -0.66
    writeFieldEnd
    -0.65
    Personendaten
    -0.63
     StatelessWidget
    -0.62
    NameInMap
    -0.62
    +#+
    -0.61
    Према
    -0.61
    POSITIVE LOGITS
     sure
    1.33
     sense
    0.98
     inroads
    0.95
     headway
    0.94
     amends
    0.94
     use
    0.91
    sure
    0.87
     gebruik
    0.79
    sense
    0.77
     adjustments
    0.75
    Activations Density 1.072%

    No Known Activations