© 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. 10818
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to chemical compositions and molecular structures

    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
    mybatisplus
    -0.64
    帖最后由
    -0.60
     محفوظة
    -0.58
     aéri
    -0.57
    delà
    -0.57
     distanciation
    -0.57
     виправивши
    -0.57
    IsContent
    -0.57
     JADX
    -0.55
    ckså
    -0.54
    POSITIVE LOGITS
    ReusableCell
    0.61
    WebElementEntity
    0.54
    isContained
    0.51
    awtextra
    0.51
     flavored
    0.50
    gdx
    0.49
     resourceCulture
    0.49
    teki
    0.48
     AttributeSet
    0.48
     lut
    0.47
    Activations Density 0.251%

    No Known Activations