© 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. 4962
    Prev
    Next
    INDEX
    Explanations

    conditions and permissions related to authority and agreements

    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
    AddTagHelper
    -0.81
    참고
    -0.74
    AccessorTable
    -0.73
    ConstraintMaker
    -0.72
    LookAnd
    -0.69
    zzleHttp
    -0.69
     SEDS
    -0.65
    NewUrlParser
    -0.65
    XmlAccessType
    -0.64
    PostExecute
    -0.63
    POSITIVE LOGITS
     or
    0.57
     explicitly
    0.46
     nor
    0.46
     der
    0.46
     von
    0.45
     rare
    0.44
     den
    0.44
     Bradbury
    0.44
     further
    0.42
     cor
    0.42
    Activations Density 0.553%

    No Known Activations