© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14198
    Prev
    Next
    INDEX
    Explanations

    terms related to warranties and liabilities in a legal context

    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
     leçons
    -0.64
     déploy
    -0.63
     détach
    -0.61
     casse
    -0.60
     célèbres
    -0.60
     ativos
    -0.60
     nakalista
    -0.58
    skrift
    -0.57
    TagMode
    -0.56
     prospet
    -0.56
    POSITIVE LOGITS
     KIND
    1.15
    KIND
    0.85
     Kind
    0.84
     kind
    0.79
    Kind
    0.77
    kind
    0.74
     StatelessWidget
    0.67
    unknownFields
    0.60
    '):
    0.60
     AssemblyCompany
    0.59
    Activations Density 0.001%

    No Known Activations