© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 987
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "go" combined with various prepositions and actions

    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
     skrzy
    -0.69
    Kuk
    -0.66
     ję
    -0.66
     Huddersfield
    -0.65
    Dud
    -0.64
     Teich
    -0.62
    minyak
    -0.62
     Sylvester
    -0.60
     Jurí
    -0.60
    JdbcTemplate
    -0.60
    POSITIVE LOGITS
    Goes
    1.34
     go
    1.31
     Goes
    1.24
     Go
    1.20
     goes
    1.19
    Go
    1.18
    going
    1.18
    goes
    1.15
     GO
    1.14
     going
    1.13
    Activations Density 0.419%

    No Known Activations