© 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. 8810
    Prev
    Next
    INDEX
    Explanations

    references to competitive achievements in cycling

    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
    ligators
    -0.55
     виправивши
    -0.54
    play
    -0.51
    HasForeignKey
    -0.51
    titleMargin
    -0.51
    BufferException
    -0.47
    ământ
    -0.46
    unjung
    -0.46
     debent
    -0.46
     nephe
    -0.45
    POSITIVE LOGITS
    WireFormat
    0.74
    IUrlHelper
    0.69
     riders
    0.69
     cyclist
    0.68
     cyclists
    0.68
     rider
    0.66
     Cycling
    0.64
     ciclista
    0.63
     bicy
    0.62
     cycling
    0.61
    Activations Density 0.016%

    No Known Activations