© 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. 24800
    Prev
    Next
    INDEX
    Explanations

    references to fiction or fictional works

    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
    Muh
    -0.67
    GEBURTS
    -0.66
     Koenig
    -0.64
     Kase
    -0.64
     kysy
    -0.63
    Precautionary
    -0.63
    posia
    -0.63
    MessageOf
    -0.62
    atra
    -0.61
     Eich
    -0.61
    POSITIVE LOGITS
     fiction
    1.34
     Fiction
    1.32
     FICTION
    1.20
    Fiction
    1.15
     Fic
    1.03
    fiction
    1.00
    Fic
    1.00
     fictional
    0.97
     fic
    0.96
     ficción
    0.92
    Activations Density 0.005%

    No Known Activations