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. 396
    Prev
    Next
    INDEX
    Explanations

    terms related to complex systems and structures, such as mathematical models and graphs

    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
    yntaxException
    -0.96
     beginnetje
    -0.82
    rungsseite
    -0.74
    Personendaten
    -0.73
    ByVersion
    -0.69
    __*/
    -0.67
    AndEndTag
    -0.66
    MethodManager
    -0.65
    richTextPanel
    -0.65
    ArgsConstructor
    -0.64
    POSITIVE LOGITS
    μως
    0.52
    ."));
    0.52
    참고
    0.50
    tshell
    0.50
    ]--;
    0.50
    들
    0.47
    Czytaj
    0.47
     pró
    0.46
    ]");
    0.46
     مشارکت‌کنندگان
    0.45
    Activations Density 6.557%

    No Known Activations