© 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. 98
    Prev
    Next
    INDEX
    Explanations

    mentions of code and programming

    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
     nazionali
    -0.60
     noastră
    -0.60
    XmlAccessType
    -0.58
     însă
    -0.58
     religieux
    -0.57
     fondament
    -0.56
     folosi
    -0.56
     près
    -0.56
     cât
    -0.55
     noastre
    -0.55
    POSITIVE LOGITS
     file
    0.73
     code
    0.73
     user
    0.70
     custom
    0.69
     *_
    0.68
     data
    0.67
     text
    0.67
     html
    0.65
     TextAppearance
    0.65
     database
    0.63
    Activations Density 5.710%

    No Known Activations