© 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. 26783
    Prev
    Next
    INDEX
    Explanations

    references to the amino acid tyrosine

    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
     Anſ
    -1.05
     Reſ
    -0.97
     ſtand
    -0.93
     viſ
    -0.90
     houſe
    -0.90
     anſ
    -0.88
    idän
    -0.87
     preſent
    -0.86
     sandero
    -0.86
     reaſon
    -0.85
    POSITIVE LOGITS
     Ty
    1.39
    rosine
    1.20
     tyrosine
    1.05
     ty
    1.04
    Ty
    1.04
    ty
    0.77
     tiros
    0.75
    jod
    0.73
     tyrant
    0.73
     Jaffe
    0.70
    Activations Density 0.011%

    No Known Activations