© 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. 11920
    Prev
    Next
    INDEX
    Explanations

    terms related to MIME types and their usage in data formats

    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
    parametrize
    -0.63
     للاسماء
    -0.58
    stä
    -0.57
     Catan
    -0.57
    DZ
    -0.56
    belec
    -0.56
    addCriterion
    -0.54
    bracelet
    -0.54
    InputBorder
    -0.53
     negeri
    -0.51
    POSITIVE LOGITS
    MIME
    1.86
     MIME
    1.83
     mime
    1.63
    mime
    1.59
    Mime
    1.54
     Mime
    1.51
    mimeType
    1.09
    MIM
    0.94
    MimeType
    0.93
     MIM
    0.84
    Activations Density 0.003%

    No Known Activations