© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9840
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to horses

    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
    |}{\
    -0.78
    cadilly
    -0.77
    _{-\
    -0.77
     Rides
    -0.76
     rides
    -0.72
    ride
    -0.72
     prit
    -0.71
    adaptiveStyles
    -0.71
     (!__
    -0.71
     تضيفلها
    -0.71
    POSITIVE LOGITS
    horses
    1.21
     horses
    1.16
    horse
    1.15
     horse
    1.08
     Horses
    1.06
    Horses
    1.04
    Horse
    0.96
     Horse
    0.93
     HORSE
    0.90
     equine
    0.78
    Activations Density 0.004%

    No Known Activations