© 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. 11079
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values or identifiers

    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
     StringTokenizer
    -0.64
     createSprite
    -0.58
     onOptions
    -0.56
     lẻ
    -0.52
    قایناق‌لار
    -0.50
     kasarigan
    -0.50
     doing
    -0.49
     standing
    -0.48
    횟
    -0.48
    RegressionTest
    -0.48
    POSITIVE LOGITS
     الحره
    0.64
    ,:]
    0.63
    %";
    0.62
    KommentareTeilen
    0.61
    DockStyle
    0.59
    migrationBuilder
    0.56
     duquel
    0.54
     annexed
    0.53
     Blackwood
    0.52
     linseed
    0.52
    Activations Density 0.032%

    No Known Activations