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. 10252
    Prev
    Next
    INDEX
    Explanations

    references to post-apocalyptic themes and settings

    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
     الرياضيه
    -0.61
     hinaus
    -0.56
     esboço
    -0.54
    ScopeManager
    -0.53
     Übung
    -0.48
     везе
    -0.48
     equiv
    -0.48
    unfinished
    -0.47
    inars
    -0.47
     domicile
    -0.46
    POSITIVE LOGITS
    MigrationBuilder
    0.83
    WaitGroup
    0.70
    AutoScale
    0.69
    Portale
    0.65
    DockStyle
    0.65
    
    0.65
    новниш
    0.61
     Paglinawan
    0.61
    Hozzáférés
    0.59
    kháu
    0.57
    Activations Density 0.097%

    No Known Activations