© 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. 30694
    Prev
    Next
    INDEX
    Explanations

    academic or technical terminology related to methodologies and frameworks

    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
    Personendaten
    -0.83
    Portály
    -0.76
    GenerationType
    -0.73
    styleType
    -0.71
     setw
    -0.71
    RenderAtEndOf
    -0.71
    TagMode
    -0.70
    AxisAlignment
    -0.69
     Monfieur
    -0.69
     HasFactory
    -0.69
    POSITIVE LOGITS
    ish
    0.42
    bis
    0.41
    льники
    0.40
    vedra
    0.40
    __":
    0.39
    tembro
    0.38
    iblichen
    0.37
     خار
    0.36
    alige
    0.36
    ộn
    0.36
    Activations Density 0.098%

    No Known Activations