© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 349
    Prev
    Next
    INDEX
    Explanations

    references to legal claims or assertions within legal documents

    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
    LEncoder
    -0.59
     vanske
    -0.58
    DllImport
    -0.57
     []:
    -0.54
     виправивши
    -0.54
     indisponible
    -0.52
    leté
    -0.52
    IntoConstraints
    -0.52
     تضيفلها
    -0.50
    achable
    -0.50
    POSITIVE LOGITS
     claim
    3.27
     claims
    3.23
     Claims
    2.89
     Claim
    2.86
     claimed
    2.81
    claims
    2.73
     CLAIM
    2.70
    claim
    2.69
    Claim
    2.69
     CLAIMS
    2.69
    Activations Density 1.428%

    No Known Activations