© 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. 5688
    Prev
    Next
    INDEX
    Explanations

    structural components and connections in mechanical or technical descriptions

    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
    Hentet
    -0.60
     mieście
    -0.50
    tonode
    -0.49
    Poppins
    -0.48
    ciles
    -0.47
    cashire
    -0.46
     conci
    -0.44
     {*}
    -0.43
    readObject
    -0.43
    tomy
    -0.42
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.77
    LayoutStyle
    0.65
     "..\..\
    0.62
     Sentences
    0.60
    setViewName
    0.59
     FetchType
    0.59
     الحره
    0.58
     "..\..\..\
    0.58
    GOTREF
    0.57
    jsxFileName
    0.56
    Activations Density 0.303%

    No Known Activations