© 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. 2932
    Prev
    Next
    INDEX
    Explanations

    references to tumor necrosis factor (TNF) and its relation to various biological processes

    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
    er
    -0.99
    ER
    -0.78
    dela
    -0.58
     McQu
    -0.58
    <strong>
    -0.55
    Gad
    -0.53
     floor
    -0.52
    gridx
    -0.52
    platt
    -0.52
    en
    -0.52
    POSITIVE LOGITS
     TNF
    2.02
    TNF
    1.94
    WriteTagHelper
    1.13
    脚注の使い方
    1.05
    PreferredItem
    1.05
    awtextra
    1.05
    dialement
    1.01
    +:+
    1.01
    thâu
    1.00
     للاسماء
    1.00
    Activations Density 0.006%

    No Known Activations