© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4838
    Prev
    Next
    INDEX
    Explanations

    references related to session management and API interactions

    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
    createServer
    -1.13
    ibatis
    -1.12
    BagLayout
    -1.05
    PerformLayout
    -1.04
    IsMutable
    -0.95
    conio
    -0.92
    XMLSchema
    -0.91
    %)$
    -0.90
    /***/
    -0.90
     OkHttpClient
    -0.89
    POSITIVE LOGITS
    ation
    1.13
    ally
    1.06
    Zon
    0.96
    sion
    0.93
     Zon
    0.90
    ed
    0.87
     Sion
    0.86
    ason
    0.82
    ion
    0.81
     session
    0.81
    Activations Density 0.423%

    No Known Activations