© 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. 22-RES-MATRYOSHKA-DC
    7. 2854
    Prev
    Next
    INDEX
    Explanations

    terminology related to genetics and mutations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    VersionUID
    -0.67
     genomes
    -0.66
     AssemblyCulture
    -0.60
    Билгалдахарш
    -0.57
     kaynağından
    -0.57
    __.__
    -0.56
     JpaRepository
    -0.56
     DNA
    -0.54
     ProtoMessage
    -0.53
    OrNil
    -0.53
    POSITIVE LOGITS
     exon
    0.85
     ex
    0.79
     Ex
    0.67
     splice
    0.64
     alternative
    0.63
     Alternative
    0.63
    Ex
    0.62
    ex
    0.60
     splicing
    0.60
     alternatif
    0.58
    Activations Density 0.390%

    No Known Activations