© 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. 32575
    Prev
    Next
    INDEX
    Explanations

    references to poetry and poets

    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
    //
    -0.81
    migrationBuilder
    -0.74
    т
    -0.74
     Hann
    -0.66
    mangle
    -0.62
    ANN
    -0.61
     Bastille
    -0.61
    dira
    -0.61
    ฉ
    -0.60
    }^{(
    -0.59
    POSITIVE LOGITS
     poetry
    1.59
    Poetry
    1.54
     Poetry
    1.53
     Poet
    1.40
    poetry
    1.40
     poet
    1.39
     poems
    1.36
     poets
    1.34
     poesia
    1.33
     Poem
    1.27
    Activations Density 0.005%

    No Known Activations