© 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. 12-RES-MATRYOSHKA-DC
    7. 6390
    Prev
    Next
    INDEX
    Explanations

    function calls related to data fetching or retrieval

    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
    
    -1.13
    BufferException
    -0.90
    uanya
    -0.78
    beelden
    -0.73
     throwable
    -0.73
    saraba
    -0.71
    lichung
    -0.71
    Datuak
    -0.69
     Schuster
    -0.69
     MainAxisSize
    -0.69
    POSITIVE LOGITS
    set
    0.78
    get
    0.68
    Denis
    0.66
    HttpGet
    0.66
    довая
    0.64
     endforeach
    0.63
    DRAW
    0.63
     openness
    0.63
     SET
    0.62
    θε
    0.62
    Activations Density 0.056%

    No Known Activations