© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 5755
    Prev
    Next
    INDEX
    Explanations

    references to horses and equestrian related terms

    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
     Nae
    -0.81
     Nadia
    -0.76
    펙
    -0.72
     Cathedral
    -0.68
    onoi
    -0.67
    NOON
    -0.67
    Архи
    -0.66
     Sarg
    -0.66
    Raum
    -0.65
     Largo
    -0.65
    POSITIVE LOGITS
     horse
    1.28
     Horse
    1.27
     horseman
    1.27
     mount
    1.22
    Horse
    1.21
     HORSE
    1.21
     horses
    1.20
     horseback
    1.19
     Horses
    1.18
    Horses
    1.15
    Activations Density 0.103%

    No Known Activations