© 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. 22847
    Prev
    Next
    INDEX
    Explanations

    ellipses indicating pauses or omissions in text

    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
     समीक्षक
    -0.74
    uxxxx
    -0.74
    Autoritní
    -0.73
     CreateTagHelper
    -0.70
     tetrach
    -0.66
    BrowserModule
    -0.65
    LookAnd
    -0.65
     himo
    -0.65
    principalTable
    -0.65
     étrang
    -0.63
    POSITIVE LOGITS
    ORIAL
    0.56
     til
    0.52
     ex
    0.50
     "..\..\
    0.50
     possible
    0.49
    ="<?=$
    0.49
     past
    0.48
    ServletConfig
    0.48
    兼
    0.48
     potential
    0.47
    Activations Density 0.004%

    No Known Activations