© 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. 28299
    Prev
    Next
    INDEX
    Explanations

    terms related to resorts and vacation destinations

    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
    ndice
    -0.68
     IndexPath
    -0.66
    räder
    -0.65
     sosial
    -0.63
     Bö
    -0.63
    ered
    -0.62
    #\
    -0.62
    BufferException
    -0.61
    Moin
    -0.60
    BoxShadow
    -0.60
    POSITIVE LOGITS
     resorts
    1.57
     resort
    1.44
    Resort
    1.30
     Resort
    1.30
     Resorts
    1.28
     resorting
    1.27
     resorted
    1.26
    resort
    1.25
    />";
    0.86
     recurrir
    0.85
    Activations Density 0.006%

    No Known Activations