© 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. 25919
    Prev
    Next
    INDEX
    Explanations

    references to floating-point data types and operations

    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
    räck
    -0.80
     Gustave
    -0.75
     propOrder
    -0.75
    ally
    -0.74
     Sheppard
    -0.74
     Lega
    -0.71
    APORE
    -0.69
    <strong>
    -0.68
    كثر
    -0.67
     Schiller
    -0.67
    POSITIVE LOGITS
     CFP
    1.10
     fp
    1.05
     FP
    1.00
    fp
    0.90
     Larissa
    0.89
    FP
    0.83
    WebControls
    0.80
     Mali
    0.79
     Gabel
    0.77
    bolista
    0.75
    Activations Density 0.128%

    No Known Activations