© 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. 19637
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to sequences or variables in probability and graph theory contexts

    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
     cherchés
    -0.62
     GenerationType
    -0.60
    TagHelper
    -0.54
     torno
    -0.53
     jPanel
    -0.52
     صوتيه
    -0.51
    :^
    -0.50
     alia
    -0.50
    ives
    -0.49
    Comments
    -0.49
    POSITIVE LOGITS
    cèse
    0.59
    XmlType
    0.59
     CURIAM
    0.57
    MergeFrom
    0.53
    NamedQueries
    0.52
    ksikon
    0.50
    SerializedSize
    0.49
     виправивши
    0.49
     culturelles
    0.49
    SharedCtor
    0.49
    Activations Density 0.050%

    No Known Activations