© 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. 17488
    Prev
    Next
    INDEX
    Explanations

    instances of the word "host" and its variations in different contexts

    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
    errHandler
    -0.69
    CompleteListener
    -0.66
    detectChanges
    -0.62
     Mestre
    -0.57
     курс
    -0.55
    /*++
    -0.54
     trebui
    -0.54
     JLabel
    -0.53
     Brunswick
    -0.52
    elson
    -0.52
    POSITIVE LOGITS
     Hosting
    1.07
    Hosting
    1.04
     hosting
    1.01
     hosted
    0.95
    hosting
    0.87
     Hosted
    0.83
    hosted
    0.78
    Hosted
    0.77
    tvguidetime
    0.71
     BoxDecoration
    0.68
    Activations Density 0.012%

    No Known Activations