© 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. 30340
    Prev
    Next
    INDEX
    Explanations

    terms related to signal loss or reduction in intensity, specifically emphasizing "attenuation."

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Hochspringen
    -0.75
     Lacy
    -0.73
    ysk
    -0.72
     Italijani
    -0.72
    ineno
    -0.71
     Drayton
    -0.71
     FRO
    -0.69
    QRect
    -0.69
     Jof
    -0.68
     Duch
    -0.68
    POSITIVE LOGITS
    atten
    1.19
     attenuation
    1.15
     attenu
    1.06
    Atten
    1.02
     attenuated
    0.99
     Atten
    0.98
     atten
    0.95
     attent
    0.79
    ##############
    0.76
    uated
    0.73
    Activations Density 0.004%

    No Known Activations