© 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. 21059
    Prev
    Next
    INDEX
    Explanations

    phrases related to the assembly and integration of components in a manufacturing or technical context

    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
    SourceChecksum
    -0.81
    ValueStyle
    -0.77
    adaptiveStyles
    -0.77
    +#+#
    -0.74
     disambiguazione
    -0.73
    rungsseite
    -0.70
    ErrUnexpectedEOF
    -0.69
    TagMode
    -0.67
    !*\
    -0.67
    )))),
    -0.67
    POSITIVE LOGITS
    quila
    0.55
     מו
    0.51
     Stack
    0.45
    Stack
    0.44
    ctools
    0.42
     Lam
    0.41
    jur
    0.40
    stack
    0.40
    eningrad
    0.40
     déchir
    0.40
    Activations Density 0.089%

    No Known Activations