© 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. 0-RES-MATRYOSHKA-DC
    7. 14453
    Prev
    Next
    INDEX
    Explanations

    references to procedural protections and legal rights related to removal proceedings

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     topics
    -1.62
     subjects
    -1.45
     Topics
    -1.38
     themes
    -1.34
    Topics
    -1.34
     Subjects
    -1.28
    topics
    -1.19
    subjects
    -1.16
     Themes
    -1.09
     SUBJECTS
    -1.07
    POSITIVE LOGITS
     subject
    0.86
    VersionUID
    0.67
    subject
    0.65
    ContentAlignment
    0.62
     protoimpl
    0.60
    reactstrap
    0.60
     pulumi
    0.57
    zzleHttp
    0.52
    mycin
    0.50
    unknownFields
    0.50
    Activations Density 0.006%

    No Known Activations