© 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. 24-RES-MATRYOSHKA-DC
    7. 1414
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with "your" needs.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ​
    -0.59
    :​
    -0.59
    ¬
    -0.57
    )​
    -0.54
    ymce
    -0.54
     intptr
    -0.53
    verifyException
    -0.53
     ujednoznacz
    -0.52
    

    -0.52
    хь
    -0.52
    POSITIVE LOGITS
    Demografie
    0.62
     depic
    0.60
     consisted
    0.59
     civils
    0.59
     concurred
    0.57
     likewise
    0.57
     vendar
    0.57
    InstanceState
    0.55
     wherefore
    0.55
     UNITED
    0.54
    Activations Density 0.061%

    No Known Activations