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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21700
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate accompaniment or association between subjects or actions

    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
     acres
    -0.65
    KELEY
    -0.63
    /***/
    -0.60
     Jahre
    -0.59
     TLR
    -0.59
    NgModule
    -0.58
     gulls
    -0.58
     blaue
    -0.58
    BooleanField
    -0.57
     Davis
    -0.57
    POSITIVE LOGITS
    companying
    1.34
     accompanies
    1.16
    companied
    1.13
     accompanying
    1.12
     accompany
    1.07
     accompag
    1.06
     accompagn
    1.05
     accompanied
    1.04
     сопрово
    1.00
    accompanied
    0.94
    Activations Density 0.007%

    No Known Activations