© 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. 6672
    Prev
    Next
    INDEX
    Explanations

    highly plausible legal or judicial claims related to discrimination or civil rights violations

    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
    opsida
    -0.61
     contrats
    -0.57
    ंदीखरीदारी
    -0.57
    CppMethod
    -0.57
    UpInside
    -0.57
     Benedetto
    -0.55
    extAlignment
    -0.52
    IsContent
    -0.51
     IBOutlet
    -0.51
     organised
    -0.50
    POSITIVE LOGITS
    tagHelperRunner
    0.69
    ništvo
    0.64
    ]--;
    0.60
     خارجية
    0.59
    onuc
    0.56
    }>;
    0.55
    });*/
    0.53
    مصادر
    0.53
    }*/
    0.53
     kaarangay
    0.52
    Activations Density 0.034%

    No Known Activations