© 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. 3683
    Prev
    Next
    INDEX
    Explanations

    references to astrophysical phenomena and research related to astronomy

    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
    ValueOf
    -0.57
    OneToMany
    -0.55
     Sharpe
    -0.54
    manuelle
    -0.52
    nsan
    -0.52
     Sop
    -0.51
     Blen
    -0.51
    entrums
    -0.51
    uluş
    -0.51
    bage
    -0.50
    POSITIVE LOGITS
     Astro
    2.66
     astro
    2.66
    Astro
    2.66
    astro
    2.02
     Astrophysics
    1.80
    ASTRO
    1.73
     астро
    1.57
     astronomy
    1.55
     astronomers
    1.54
     Astrology
    1.54
    Activations Density 0.078%

    No Known Activations