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. 26903
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a source or origin

    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
     насељу
    -0.76
    passage
    -0.63
    例句
    -0.63
     />';
    -0.62
     Hame
    -0.61
     ExecuteAsync
    -0.61
    🐄
    -0.60
     Meck
    -0.59
    dyž
    -0.59
    jsonwebtoken
    -0.58
    POSITIVE LOGITS
    migrationBuilder
    0.65
    TagMode
    0.62
     Permanente
    0.60
    dhist
    0.56
     Madura
    0.55
    enial
    0.53
     Shawnee
    0.51
    usal
    0.51
    GetWindow
    0.51
    terness
    0.50
    Activations Density 0.014%

    No Known Activations