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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16415
    Prev
    Next
    INDEX
    Explanations

    references to specific geological time periods and locations

    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
     дописавши
    -0.69
     continúas
    -0.66
    ReusableCell
    -0.66
    rungsseite
    -0.65
    rophoto
    -0.64
    tagext
    -0.63
    SharedDtor
    -0.62
    +#+#
    -0.61
     ComVisible
    -0.60
    bcryptjs
    -0.60
    POSITIVE LOGITS
     sele
    0.57
     سا
    0.48
    ero
    0.46
    IAB
    0.46
    мую
    0.46
    ussi
    0.46
    Broad
    0.45
    penn
    0.45
     penna
    0.44
     Hanna
    0.44
    Activations Density 0.015%

    No Known Activations