© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 448
    Prev
    Next
    INDEX
    Explanations

    HTML tags, particularly paragraph beginnings, hyperlinks, and images

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.67
    kloped
    -0.61
    tvguidetime
    -0.60
     Italijanski
    -0.60
    ">:
    -0.59
     CURIAM
    -0.58
    
    -0.58
    ListItemIcon
    -0.57
    asional
    -0.56
    ⟬
    -0.56
    POSITIVE LOGITS
     class
    1.20
     id
    0.83
    class
    0.83
     style
    0.65
     data
    0.59
     classe
    0.58
    BindingResult
    0.55
     name
    0.54
     CLASS
    0.54
     href
    0.53
    Activations Density 0.329%

    No Known Activations