© 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. 1477
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to proteins, amino acids, and glycosylation.

    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
     SafeMath
    -0.58
     disambiguazione
    -0.56
     Pharisees
    -0.52
     فريبيس
    -0.51
    reactstrap
    -0.51
    intellij
    -0.51
    ymce
    -0.50
     nutmeg
    -0.49
     COMMIT
    -0.48
    benzene
    -0.48
    POSITIVE LOGITS
     peptides
    0.84
     antigen
    0.71
     antibodies
    0.71
     antigens
    0.69
     peptide
    0.68
     proteins
    0.66
     polypep
    0.65
     polypeptide
    0.64
     Antibodies
    0.64
     protein
    0.63
    Activations Density 1.656%

    No Known Activations