© 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. 17087
    Prev
    Next
    INDEX
    Explanations

    references to calibration data

    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
     وتسجيلات
    -0.84
    %";
    -0.76
    RSpec
    -0.74
    ?<
    -0.74
    ."<
    -0.72
    ]";
    -0.71
     invi
    -0.69
    })));
    -0.68
     églises
    -0.67
    )';
    -0.64
    POSITIVE LOGITS
    ibrated
    1.37
     calibrate
    1.28
     calibr
    1.10
     Calibration
    1.09
     calibration
    1.08
     calibrated
    1.07
    Calibration
    1.05
    calibration
    1.01
    ibrate
    0.96
     calib
    0.91
    Activations Density 0.003%

    No Known Activations