© 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. 24-RES-MATRYOSHKA-DC
    7. 900
    Prev
    Next
    INDEX
    Explanations

    uses of the word "to" in the context of movement and location

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.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
     all
    -0.56
    ніципа
    -0.49
    czegó
    -0.48
    ষ্
    -0.48
    }'.
    -0.47
    erunner
    -0.47
    את
    -0.46
     للاسماء
    -0.45
    ิจ
    -0.44
     Itself
    -0.44
    POSITIVE LOGITS
     town
    0.80
     bed
    0.75
     jail
    0.74
     chez
    0.73
     church
    0.72
     kantoor
    0.71
     school
    0.71
     skolan
    0.68
     court
    0.65
    بوابة
    0.64
    Activations Density 1.209%

    No Known Activations