© 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. 17602
    Prev
    Next
    INDEX
    Explanations

    references to "halo" in a scientific context, particularly in relation to dark matter models

    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
     Sopho
    -0.82
     sério
    -0.82
     anteriore
    -0.79
     Broughton
    -0.79
     Allegretto
    -0.76
     navires
    -0.75
    BASEPATH
    -0.75
     Stedman
    -0.74
     CreateTagHelper
    -0.74
    SYSC
    -0.73
    POSITIVE LOGITS
     halo
    1.73
     Halo
    1.61
    Halo
    1.44
    halo
    1.43
     halos
    1.31
    rogels
    0.69
     HAL
    0.66
    NameInMap
    0.66
     Ban
    0.65
    iecie
    0.62
    Activations Density 0.003%

    No Known Activations