© 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. 21931
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements and structures, particularly related to functions and methods

    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
    NameInMap
    -0.82
     protoimpl
    -0.68
    oredCriteria
    -0.60
    WriteBarrier
    -0.59
    новниш
    -0.58
    jspb
    -0.56
    ніципа
    -0.55
    findpost
    -0.51
     Bourgoin
    -0.51
    Carriera
    -0.50
    POSITIVE LOGITS
     esternos
    0.58
    पया
    0.57
     adjoint
    0.57
    DropTable
    0.56
     socialista
    0.55
     relever
    0.54
     frère
    0.54
     abstrato
    0.54
     Vierge
    0.53
    Nyc
    0.53
    Activations Density 0.036%

    No Known Activations