© 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. 29312
    Prev
    Next
    INDEX
    Explanations

    legal arguments and claims made in a trial 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
    Negative Logits
    DeleteBehavior
    -0.82
    NameInMap
    -0.82
    MLLoader
    -0.81
     Réponses
    -0.74
     ProtoMessage
    -0.73
    клопе
    -0.71
    otriva
    -0.71
    ="@+
    -0.70
     تضيفلها
    -0.69
    EDEFAULT
    -0.69
    POSITIVE LOGITS
    FindAll
    0.49
    )):
    0.46
    alty
    0.46
    }');
    0.45
     Wallis
    0.45
     Pascual
    0.45
     Dickerson
    0.45
     working
    0.44
     Lipp
    0.44
    alha
    0.44
    Activations Density 0.049%

    No Known Activations