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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 4989
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and relationships between values

    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
     FetchType
    -0.82
    ArgsConstructor
    -0.79
    apimachinery
    -0.72
    yntaxException
    -0.68
    onViewCreated
    -0.65
    GeneratedValue
    -0.65
    Искәрмәләр
    -0.61
     gynhyrchwyd
    -0.60
    ędzynarod
    -0.59
    inazione
    -0.58
    POSITIVE LOGITS
     OMITBAD
    0.66
    stretchr
    0.58
     inequality
    0.57
    érial
    0.54
     söz
    0.53
     énergé
    0.52
    UnitTesting
    0.50
    wiſe
    0.50
     becauſe
    0.50
    IntoConstraints
    0.50
    Activations Density 0.344%

    No Known Activations