© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 539
    Prev
    Next
    INDEX
    Explanations

    terms related to protection and security

    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
     Madd
    -0.68
    LLocation
    -0.63
    ="@+
    -0.62
     CreateTagHelper
    -0.61
     Kettle
    -0.61
    moveToFirst
    -0.61
    DidLoad
    -0.60
    doit
    -0.59
    complexContent
    -0.59
     GetEnumerator
    -0.59
    POSITIVE LOGITS
     protection
    1.55
     protects
    1.54
     protect
    1.51
     Protect
    1.51
     protecting
    1.48
     Protects
    1.44
     protections
    1.43
    Protect
    1.42
    protection
    1.41
     Protection
    1.39
    Activations Density 0.832%

    No Known Activations