Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 15556
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to protein interactions and modifications

    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
    play
    -0.43
     played
    -0.38
    ODB
    -0.37
     Acción
    -0.36
     Teufel
    -0.35
    ंस
    -0.34
    Play
    -0.34
     Coleridge
    -0.34
    PLAY
    -0.34
    ाली
    -0.34
    POSITIVE LOGITS
    rungsseite
    1.07
    expandindo
    1.02
     насељу
    0.95
    ThroughAttribute
    0.89
    URLException
    0.82
     فريبيس
    0.77
     ProtoMessage
    0.77
    SBATCH
    0.75
    BeginContext
    0.75
    contentLoaded
    0.74
    Activations Density 0.068%

    No Known Activations