© 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. 25545
    Prev
    Next
    INDEX
    Explanations

    references to "beating" or "beat," particularly in competitive or aggressive contexts

    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
    EndContext
    -1.02
    PerformLayout
    -1.00
    DockStyle
    -0.90
    adaptiveStyles
    -0.82
     (!__
    -0.81
    unhofer
    -0.81
     ECR
    -0.79
    RegistryLite
    -0.78
     autorytatywna
    -0.77
    potranspiration
    -0.77
    POSITIVE LOGITS
     Beat
    1.66
     BEAT
    1.65
     Beats
    1.59
     beat
    1.58
     beats
    1.56
    Beat
    1.52
    beats
    1.43
    BEAT
    1.39
    Beats
    1.38
    beat
    1.37
    Activations Density 0.015%

    No Known Activations