© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 18898
    Prev
    Next
    INDEX
    Explanations

    terms related to data transmission and encoding processes

    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
    Negative Logits
    WebElementEntity
    -0.63
    jooq
    -0.51
    wsdl
    -0.50
     säll
    -0.47
    esac
    -0.46
    inetto
    -0.46
     defaultdict
    -0.45
     mass
    -0.45
     TE
    -0.45
    läufe
    -0.45
    POSITIVE LOGITS
     linkovi
    0.83
    Gambas
    0.63
     gubern
    0.60
     Вікі
    0.59
     beggars
    0.59
    原始内容存档于
    0.59
    calaureate
    0.57
     Eurovision
    0.56
    itemBuilder
    0.56
     Chwiliwch
    0.56
    Activations Density 0.079%

    No Known Activations