© 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. 3908
    Prev
    Next
    INDEX
    Explanations

    references to astrophysical models, data analysis processes, and observations related to cosmic microwave background and primordial signals

    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
     createSlice
    -0.69
     Taktlose
    -0.64
    __':
    -0.61
    DataAnnotations
    -0.58
     OMITBAD
    -0.57
    ADELPHIA
    -0.54
    #+#
    -0.54
    HomeAsUpEnabled
    -0.53
    createClass
    -0.51
     Seeder
    -0.50
    POSITIVE LOGITS
    DrawerToggle
    0.69
     Telescope
    0.65
    ########.
    0.60
     telescopes
    0.59
     exposure
    0.55
     Hama
    0.54
    Carriera
    0.53
    IsMutable
    0.53
     exposures
    0.52
    MethodManager
    0.52
    Activations Density 0.314%

    No Known Activations