© 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. 20377
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe characteristics or qualities

    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
     Delia
    -0.86
     Paglinawan
    -0.86
    fecture
    -0.84
     crows
    -0.83
     virgins
    -0.83
     virginity
    -0.81
     imputation
    -0.81
    manteau
    -0.79
    ausea
    -0.79
    Slf
    -0.79
    POSITIVE LOGITS
    idal
    0.67
    cing
    0.59
    led
    0.56
    }')
    0.56
    zyła
    0.56
     pá
    0.56
    ided
    0.56
    cer
    0.52
    ced
    0.52
    InstanceOf
    0.52
    Activations Density 0.040%

    No Known Activations