© 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. 12-RES-MATRYOSHKA-DC
    7. 8716
    Prev
    Next
    INDEX
    Explanations

    mentions of galaxies or related astronomical terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
     podjela
    -0.70
    homonymie
    -0.69
     bpy
    -0.65
     Eugenia
    -0.64
     Stamps
    -0.60
     stamps
    -0.59
    nodoc
    -0.59
    XV
    -0.58
     IBA
    -0.56
    loger
    -0.55
    POSITIVE LOGITS
     Galactic
    1.13
    Galactic
    1.00
     Milky
    0.95
    GEBURTSDATUM
    0.94
     galactic
    0.90
    slidesPer
    0.75
    +#+#
    0.75
     tremp
    0.71
     interstellar
    0.68
     plaisir
    0.64
    Activations Density 0.001%

    No Known Activations