© 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. 21412
    Prev
    Next
    INDEX
    Explanations

    complex mathematical expressions and relationships

    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
     skå
    -0.46
    â
    -0.45
     justiça
    -0.43
     disfrutando
    -0.42
    }}_
    -0.42
     fær
    -0.42
     Lengkap
    -0.42
    оте
    -0.42
    ________________
    -0.40
     proprement
    -0.40
    POSITIVE LOGITS
    RectangleBorder
    1.05
    expandindo
    1.05
    PhysRevD
    0.95
    ########.
    0.93
    XmlAccessorType
    0.91
    IntoConstraints
    0.90
    IRQn
    0.88
    PageModule
    0.88
    tagHelperRunner
    0.85
     BorderSide
    0.85
    Activations Density 0.076%

    No Known Activations