© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 5408
    Prev
    Next
    INDEX
    Explanations

    specific numerical or coded references in a document

    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
    <bos>
    -0.63
    newState
    -0.54
    PAIGN
    -0.51
    phemy
    -0.49
    riwal
    -0.49
    guien
    -0.47
     invitados
    -0.46
    PARTIC
    -0.45
    uxxxx
    -0.45
     Fore
    -0.45
    POSITIVE LOGITS
     disambiguazione
    0.95
     שוליים
    0.78
    Hentet
    0.76
     nahilalakip
    0.76
    TestingModule
    0.75
    featureID
    0.69
    abstractmethod
    0.69
    InjectAttribute
    0.68
    MemoryWarning
    0.68
    awaiter
    0.66
    Activations Density 0.251%

    No Known Activations