© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 273
    Prev
    Next
    INDEX
    Explanations

    terms related to cellular morphology and dynamics in biological studies

    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
     Efq
    -0.73
     sessile
    -0.72
     finitely
    -0.69
     dischar
    -0.68
     Pública
    -0.68
     tubercle
    -0.67
     Hopf
    -0.67
     [{
    -0.66
     quæ
    -0.66
     ſeveral
    -0.66
    POSITIVE LOGITS
     shape
    1.00
     structure
    0.92
     layout
    0.85
     shapes
    0.84
     SHAPE
    0.82
     patterns
    0.82
     Shape
    0.81
     pattern
    0.79
    shape
    0.79
     features
    0.78
    Activations Density 4.919%

    No Known Activations