© 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. 32003
    Prev
    Next
    INDEX
    Explanations

    terms related to 'pedal' and 'bicycle' features

    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
    Negative Logits
    fromCharCode
    -0.81
     Sama
    -0.71
     Mako
    -0.68
    POI
    -0.68
     Blot
    -0.66
    ็จ
    -0.64
     Márquez
    -0.64
    {
    -0.64
    ombras
    -0.64
    strato
    -0.62
    POSITIVE LOGITS
     Ped
    1.55
     ped
    1.48
     Pedersen
    1.46
     pedals
    1.45
     PED
    1.43
    Ped
    1.38
    ped
    1.05
     pedestal
    1.03
     pedestrians
    1.00
    PED
    0.98
    Activations Density 0.005%

    No Known Activations