© 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. 6344
    Prev
    Next
    INDEX
    Explanations

    content related to evaluations and assessments of entities or processes

    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
    kuuta
    -0.58
    principalTable
    -0.57
    errHandler
    -0.55
    ModelSerializer
    -0.53
    EndInit
    -0.50
     فريبيس
    -0.50
    нусы
    -0.48
     pinulongan
    -0.48
    fromnode
    -0.47
     AssemblyCulture
    -0.47
    POSITIVE LOGITS
     approximately
    0.92
     approxim
    0.86
     total
    0.84
     roughly
    0.84
     average
    0.82
     estimated
    0.81
    approximately
    0.81
     approx
    0.79
     약
    0.76
     approximate
    0.74
    Activations Density 1.112%

    No Known Activations