Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 15734
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "typename" in template programming language syntax

    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
    HomeAsUpEnabled
    -0.66
    URLException
    -0.58
     adresu
    -0.57
    withstanding
    -0.57
    UnusedPrivate
    -0.56
     Hift
    -0.54
    ​—
    -0.51
     Tartu
    -0.50
     altrett
    -0.50
     Koran
    -0.50
    POSITIVE LOGITS
     typename
    1.02
     Chwiliwch
    0.88
    MigrationBuilder
    0.75
     InputDecoration
    0.75
     typelib
    0.73
    Jeografia
    0.73
    RectangleBorder
    0.71
    stdc
    0.71
    mybatisplus
    0.70
    posedge
    0.69
    Activations Density 0.001%

    No Known Activations