© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 28405
    Prev
    Next
    INDEX
    Explanations

    messages related to programming and system functions

    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
     endfor
    -0.52
    Einzelnachweise
    -0.48
    ussi
    -0.46
    brainly
    -0.44
    setContentView
    -0.43
    닙
    -0.42
    titu
    -0.42
     EU
    -0.40
    編成
    -0.40
    Moderator
    -0.40
    POSITIVE LOGITS
     gyhoeddwyd
    0.81
    ArrowToggle
    0.77
     protoimpl
    0.76
    rawDesc
    0.73
     autorytatywna
    0.72
    ngdoc
    0.71
    tagext
    0.70
     Administrativna
    0.68
    :✨
    0.66
     Biôgrafia
    0.65
    Activations Density 0.043%

    No Known Activations