© 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. 24294
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison and improvements in quality or efficiency

    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
     препратки
    -0.75
    RectangleBorder
    -0.73
    ớt
    -0.63
    ByVersion
    -0.63
     ligiloj
    -0.61
    AuthProvider
    -0.61
    DispatchToProps
    -0.60
     useAuth
    -0.60
     Waray
    -0.59
     myſelf
    -0.59
    POSITIVE LOGITS
    netbeans
    0.53
    EIF
    0.50
     completos
    0.48
    intios
    0.47
     vapa
    0.47
     kanssa
    0.47
     atual
    0.47
     поводу
    0.47
     preparar
    0.47
     mukaan
    0.47
    Activations Density 0.134%

    No Known Activations