© 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. 16873
    Prev
    Next
    INDEX
    Explanations

    elements related to diagrams and illustrations in technical descriptions

    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
    tvguidetime
    -0.64
    GraphicsUnit
    -0.58
    日閲覧
    -0.58
    ScopeManager
    -0.54
    createNewFile
    -0.54
    isches
    -0.54
    MethodManager
    -0.52
    Enders
    -0.52
    VersionUID
    -0.52
    migrationBuilder
    -0.51
    POSITIVE LOGITS
    BeginContext
    0.64
     NSCoder
    0.57
    tour
    0.48
     편
    0.47
    MergeFrom
    0.47
     Popov
    0.47
     bình
    0.46
     AttributeSet
    0.44
    digkeit
    0.44
    oriasis
    0.44
    Activations Density 0.007%

    No Known Activations