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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 7302
    Prev
    Next
    INDEX
    Explanations

    references to poetry or poetic works

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ://"
    -0.62
     FetchType
    -0.57
    orb
    -0.56
    setBounds
    -0.56
     Band
    -0.54
    Hansen
    -0.54
    ://
    -0.53
     kan
    -0.52
     Hansen
    -0.52
    //
    -0.52
    POSITIVE LOGITS
     poetry
    2.94
     poems
    2.83
     poem
    2.78
     Poetry
    2.64
    Poetry
    2.52
    poetry
    2.42
     Poem
    2.41
     Poems
    2.36
     poet
    2.33
     poets
    2.30
    Activations Density 0.032%

    No Known Activations