© 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. 22196
    Prev
    Next
    INDEX
    Explanations

    references to albumin and related proteins

    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
    NegativeButton
    -0.81
     Medina
    -0.64
     "\\
    -0.63
    substack
    -0.60
    <b>
    -0.57
    tokenize
    -0.56
    …………………………………………
    -0.56
    ZEL
    -0.56
    восто
    -0.56
     '../../
    -0.55
    POSITIVE LOGITS
     albumin
    1.40
     BSA
    1.39
    BSA
    1.07
    SBATCH
    0.86
    RegistryLite
    0.78
    adə
    0.74
    unschweig
    0.72
    FontOfSize
    0.72
     Normdatei
    0.71
    تقاوى
    0.71
    Activations Density 0.001%

    No Known Activations