© 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. 4277
    Prev
    Next
    INDEX
    Explanations

    terms related to viral research and discussions about liability in contexts such as insurance

    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
    :✨
    -0.75
     referenties
    -0.62
    AndEndTag
    -0.58
     ExecuteAsync
    -0.56
    onghi
    -0.56
    ostro
    -0.56
    ysuckle
    -0.55
     and
    -0.55
    pholes
    -0.54
    AxisAlignment
    -0.54
    POSITIVE LOGITS
     linkovi
    0.59
     withal
    0.59
     dessutom
    0.57
    UserScript
    0.56
    ugc
    0.55
     Chwiliwch
    0.55
     estimés
    0.55
    AnimationsModule
    0.54
     Martian
    0.54
     thence
    0.53
    Activations Density 0.336%

    No Known Activations