© 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. 10929
    Prev
    Next
    INDEX
    Explanations

    negative values or expressions involving subtraction and negative numbers

    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
     للمعارف
    -0.61
     مرئيه
    -0.58
    elski
    -0.53
    AXB
    -0.53
    BufferException
    -0.52
    роза
    -0.52
    tidae
    -0.52
    UDI
    -0.52
    Sklici
    -0.52
    henswürdigkeiten
    -0.52
    POSITIVE LOGITS
    InjectAttribute
    0.60
     Signalez
    0.60
    slidesToShow
    0.57
    énario
    0.56
     scaler
    0.55
    enumii
    0.55
    Geografía
    0.54
    expandindo
    0.54
    TagMode
    0.53
     consultato
    0.53
    Activations Density 0.011%

    No Known Activations