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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 172
    Prev
    Next
    INDEX
    Explanations

    references to visual content and the act of seeing or viewing something

    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
     bezeichneter
    -0.93
     @"/
    -0.86
     Poehler
    -0.80
    Boli
    -0.79
     Marek
    -0.77
    JpaRepository
    -0.75
     anhydride
    -0.73
     Mesopo
    -0.72
     XNUMX
    -0.71
     NgModule
    -0.71
    POSITIVE LOGITS
     see
    1.73
    see
    1.61
     sees
    1.61
    See
    1.59
     Sees
    1.55
     SEE
    1.55
     See
    1.52
     saw
    1.44
     seen
    1.41
    SEE
    1.36
    Activations Density 1.094%

    No Known Activations