© 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. 5653
    Prev
    Next
    INDEX
    Explanations

    structured data and code elements

    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
    IContainer
    -0.92
    enumii
    -0.67
     bezeichneter
    -0.67
     /\.(
    -0.64
    DOCTYPE
    -0.63
     snippetHide
    -0.63
     nakalista
    -0.62
    CodeAttribute
    -0.59
    VersionUID
    -0.59
    WebVitals
    -0.59
    POSITIVE LOGITS
     ujednoznacz
    0.55
    Zeneca
    0.51
    phazard
    0.49
    hmä
    0.47
    Rohy
    0.47
    теризу
    0.46
    lidge
    0.46
    前は
    0.46
     dotyczą
    0.46
     representing
    0.45
    Activations Density 0.744%

    No Known Activations