© 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. 1620
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there" and its variations in context

    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
    s
    -0.82
    dymyr
    -0.70
    тний
    -0.69
     Frankel
    -0.68
    nbsp
    -0.68
    фициальный
    -0.68
     Colman
    -0.68
     Schultz
    -0.68
    لينكات
    -0.66
    dillo
    -0.66
    POSITIVE LOGITS
    there
    1.09
    There
    0.98
     There
    0.95
     there
    0.94
     THERE
    0.93
     CreateTagHelper
    0.86
    THERE
    0.83
     Thier
    0.82
    enumi
    0.78
     nere
    0.77
    Activations Density 0.499%

    No Known Activations