© 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. 5664
    Prev
    Next
    INDEX
    Explanations

    labels or tags in a mathematical or scientific context

    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
     continuing
    -0.43
    ：
    -0.41
     doch
    -0.40
    :
    -0.40
    тори
    -0.40
     continued
    -0.39
    hasNext
    -0.38
    umb
    -0.37
     effect
    -0.36
     let
    -0.36
    POSITIVE LOGITS
    SpringBootTest
    0.81
    drawSprites
    0.81
     estimés
    0.78
    MessageOf
    0.78
    󠁿
    0.76
    TypedDataSet
    0.76
     BorderSide
    0.75
    webElementGuid
    0.72
    Datuak
    0.72
    iettivo
    0.72
    Activations Density 0.010%

    No Known Activations