© 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. 20502
    Prev
    Next
    INDEX
    Explanations

    legal claims and associated terms

    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
    Negative Logits
     claim
    -0.78
    CLAIM
    -0.77
     Claim
    -0.73
     claimed
    -0.71
     CLAIM
    -0.70
     claiming
    -0.69
    alleg
    -0.68
    enumi
    -0.67
     claims
    -0.66
    Claim
    -0.66
    POSITIVE LOGITS
    tanleria
    0.78
    ніципалі
    0.72
    abestanden
    0.71
    schild
    0.69
    istoitu
    0.68
     архивлан
    0.65
    ">//
    0.64
     Moderato
    0.64
     strtotime
    0.63
    GEBURTSDATUM
    0.63
    Activations Density 0.017%

    No Known Activations